Radar data analysis and hidden object detection

Abstract

Techniques are described herein for analyzing radar data to determine whether radar noise from one or more target detections may conceal additional objects in the vicinity of the target detection. Determining whether an object may be concealed may be based at least in part on the radar noise level based on the target detection, as well as on a radar cross section and / or a distribution of Doppler data associated with a particular object type. For locations in the vicinity of the target detection, the radar system may determine an estimated noise level and compare the estimated noise level to a radar cross section probability associated with the object type to determine the likelihood that an object of the object type may be concealed at the location. Based on the analysis, the system may determine a vehicle trajectory or otherwise control the vehicle based on the likelihood that an object may be concealed at the location.

Description

Technical Field

[0001] The present disclosure relates to radar data analysis and hidden object detection.

Background Art

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Patent Application No. 17 / 384,430, filed on July 23, 2021, entitled "RADAR Data Analysis and Hidden Object Detection", the entire contents of which are incorporated herein by reference for all purposes.

[0003]

[0002] Radar generally measures the distance from a radar device to the surface of an object by transmitting radio waves and receiving reflections of the radio waves from the surface of the object, and the distance can be read by a sensor of the radar device. The sensor may generate a signal based at least in part on radio waves incident on the sensor. While this signal may include a return signal resulting from reflection, the signal may also include portions resulting from noise and / or other interfering signals, either from the radar device itself or from an external source. To distinguish return signals from noise or other interfering signals, radar devices generally use a detection threshold to suppress false positive detection (i.e., identifying a portion of a signal as a return when that portion of the signal actually results from noise and / or other interfering signals). However, in some situations, such suppression can be problematic (and dangerous) because it may be associated with an actual return.

Prior Art Literature

Patent Literature

[0004]

Patent Document 1

Brief Description of the Drawings

[0005]

[0003] A detailed explanation is provided with reference to the attached drawings. In the drawings, the leftmost digit of a reference number identifies the drawing in which that reference number first appears. The use of the same reference number in different drawings indicates similar or identical items or features.

[0006] [Figure 1]

[0004] Figure 1 shows an exemplary scenario in one or more embodiments of the present disclosure in which a radar device of an autonomous vehicle receives and analyzes radar data that includes data in which an object may be obscured by radar noise associated with the detection. [Figure 2]

[0005] Figure 2 shows exemplary radar cross-sectional distributions and exemplary Doppler distributions associated with pedestrian object types according to one or more embodiments of the present disclosure. [Figure 3]

[0006] Figure 3 shows exemplary radar data, including detection, estimated noise level, and radar return signal, based on pedestrians in the environment, according to one or more embodiments of the present disclosure. [Figure 4]

[0007] Figure 4 shows an exemplary grid map of the environment associated with an autonomous vehicle, including a display of drivable and non-drivable areas based on radar noise levels and object type-specific thresholds, according to one or more embodiments of the present disclosure. [Figure 5]

[0008] Figure 5 is a graph showing the distance and Doppler delta between a detection and an object close to the detection, according to one or more embodiments of the present disclosure. [Figure 6]

[0009] Figure 6 is a flowchart illustrating an exemplary process according to one or more embodiments of the present disclosure for determining drivable and non-drivable surfaces and controlling a vehicle based on radar data analysis. [Figure 7]

[0010] Figure 7 shows a radar data model for determining the probability of a location-hidden object based on Doppler range probability and corresponding radar response threshold, according to one or more embodiments of the present disclosure. [Figure 8]

[0011] Figure 8 is a flowchart illustrating another exemplary process for determining drivable and non-drivable surfaces for controlling a vehicle based on radar data analysis, according to one or more embodiments of the present disclosure. [Figure 9]

[0012] Figure 9 is a block diagram of an exemplary system for implementing the various technologies described herein. [Modes for carrying out the invention]

[0007]

[0013] The techniques discussed herein relate to analyzing radar data generated by a vehicle moving through an environment and determining whether radar noise based on the detection of one or more targets may potentially conceal additional objects in the vicinity of the detected target. As illustrated in the various examples below, a radar system may determine radar noise levels based on the sidelobe levels associated with the detected target in the environment. Radar response thresholds, including radar cross-section (RCS) thresholds and / or Doppler thresholds associated with a particular object type, may be determined based on the radar response distribution associated with the object type. For example, one or more radar response thresholds may be calculated based on the distribution from a pedestrian object type and a predetermined probability and / or confidence threshold (e.g., 95%) associated with the detection of pedestrians in radar noise. For a particular location (or area) close to a target detection, the radar system may determine an estimated noise level for that location and compare the estimated noise level to the RCS and / or Doppler thresholds associated with one or more object types to determine the likelihood that an object of that object type may be concealed at that location. Based on the analysis of radar data, a vehicle may determine its trajectory or otherwise control its movement based on the likelihood that one or more objects may be obscured in its position.

[0008]

[0014] Analysis of radar data for object detection may include techniques to reduce or suppress false positive detections. False positive detection may include the determination of object detection in radar data caused by radar noise rather than physical objects in the environment. Conventional techniques for suppressing radar false positive detection include determining a detection threshold to reduce the number of false positive detections and / or keeping the number of false positive detections below a specified false positive detection rate. For example, constant false alarm probability techniques (CFAR), such as cell-averaged CFAR (CA-CFAR), may test each cell (or portion) of radar data to determine whether the signal associated with the target cell meets or exceeds a detection threshold determined by averaging the signal of the target cell and / or the signals associated with the cells around the target cell. Such techniques assume that if the target cell contains a return signal (e.g., radar response data indicating a detected object), the surrounding or nearby cells are likely to provide a good estimate of radar noise in the scanned area. Other techniques may be used alternatively or additionally to CFAR techniques, such as selecting the largest portion of the signal associated with a cell as the return signal.

[0009]

[0015] However, applying false positive detection suppression techniques to radar data may tend to increase the number of false detections, as response signals generated by physical objects detected in the environment are attributed to and suppressed by radar noise. For example, estimating radar noise in the environment may mask radar detection of objects smaller and / or less reflective than the noise threshold. In the case of autonomous vehicles, false radar detections, representing a failure to identify physical objects in the environment, can pose a significant risk to the safety of the vehicle, occupants, and the surrounding environment.

[0010]

[0016] To address the technical problems of radar false positive and false negative detection, the techniques discussed herein may include determining thresholds based on the radar response distribution of a particular object type to determine drivable and undrivable surfaces for vehicles in an environment. As illustrated in the various examples below, a radar noise estimator may use the location and attributes of a detected target in the radar data to determine an estimated radar noise level at other locations near the detected target. An object type threshold component may determine various thresholds (e.g., RCS and / or Doppler thresholds) associated with a particular object type (e.g., pedestrians) that can be compared to noise levels at various locations in the environment to determine drivable and undrivable surfaces.

[0011]

[0017] An impassable surface can be an area / location in an environment where the radar noise level is sufficiently high (e.g., meeting or exceeding a threshold) that the area potentially obscures one or more objects. Physical objects may or may not be present at the location of an impassable surface, but the radar noise may effectively render the impassable surface unscannly by radar devices. Therefore, a vehicle's control and navigation system may assume that each location on an impassable surface (e.g., one or more radar cells) contains an object, even if it cannot verify the presence of an object. In contrast, an impassable surface can be an area / location in an environment where the radar noise level is below a threshold, indicating that the radar noise can obscure objects with a given probability or confidence. As will be described in more detail below, the thresholds used to determine impassable and impassable surfaces can be associated with a given probability based on a specific object type (e.g., pedestrians) and object distribution. For example, the threshold might be a value determined to include 95% of radar responses from pedestrians in the environment. Different thresholds may be different values ​​determined to include a predetermined percentage of radar responses from different percentages of pedestrians in the environment (e.g., 90%, 99%) or different object types (e.g., bicycles, cars, animals). As will be described in more detail below, object type-specific radar response thresholds may include signal power values ​​(e.g., RCS values, or other indicators of radar reflected power or intensity), Doppler values, or a combination of power and Doppler values.

[0012]

[0018] In some examples, the radar response threshold associated with an object type may be determined based on a predetermined probability value for an object of that object type. For example, a pedestrian RCS distribution may be used to determine a corresponding RCS threshold based on a desired probability of 95% for a pedestrian, and / or a pedestrian Doppler distribution may be used to determine a corresponding Doppler threshold. In other examples, a predetermined threshold may be used to determine a corresponding probability (or confidence level) associated with the threshold. For example, a pedestrian RCS distribution may be used to determine the percentage of pedestrians exceeding a threshold based on an RCS radar response threshold of -50 dB. The percentage of pedestrians exceeding the threshold may also correspond to the likelihood that, if the pedestrian is present at that location in the radar data, its RCS will exceed the threshold and that the pedestrian is visible to a radar system applying that threshold as the noise level threshold.

[0013]

[0019] Object-type radar response thresholds, including RCS thresholds and / or Doppler thresholds, may also be modified upward or downward during vehicle operation to improve vehicle safety and / or driving efficiency as needed. For example, a vehicle component may adjust the radar response thresholds used for one or more object types to change the drivable and non-drivable surfaces determined for the vehicle based on the thresholds. For instance, if the environment surrounding the vehicle does not contain enough drivable surfaces to allow the vehicle to move through the environment, the object-type threshold component may increase the radar response threshold to increase the amount of drivable surface available to the vehicle. Conversely, if the environment contains more drivable surfaces, the object-type threshold component may increase one or more radar response thresholds to increase the confidence level that potential objects could not be obscured by radar noise in the environment.

[0014]

[0020] As will be explained in more detail below, in some examples, multiple different thresholds may be defined for different Doppler ranges. In some examples, the estimated radar noise level of a region in the environment may be based on the difference in radar range between the region and a nearby target detection location, or on the difference in radar measurements (e.g., Doppler and / or RCS) between the region and the target detection location. For example, as the Doppler difference between a target detection location and another location increases, the estimated noise level at the other location may decrease. As a result, different radar signal power (e.g., RCS) thresholds may be determined and applied to different Doppler ranges. Different thresholds may be evaluated for different Doppler ranges and used together with the associated object-specific probabilities for the different Doppler ranges to determine the total probability that an object of a particular object type can be hidden at that location (e.g., by summing the separate probabilities for the different Doppler ranges).

[0015]

[0021] In at least some examples, multiple decisions may be made regarding object types that vary in radar data. In the case of radar data mapping, such as cell grids, non-grid mapping, and / or radar data contours, drivable and non-drivable surface maps may be determined for a vehicle with respect to one or more different object types. For example, a drivable / non-drivable surface map based on potentially hidden pedestrians may differ from a map based on potentially hidden cyclists, etc. In some examples, an autonomous vehicle may generate a trajectory to control its operation based at least partially on one or more drivable / non-drivable surface maps, according to the techniques discussed herein. Additionally or alternatively, an autonomous vehicle may activate collision avoidance systems (CAS), remotely operated computing devices, and / or engage or disengage certain autonomous driving features based on the drivable / non-drivable surface maps and / or determinations of potentially hidden objects, according to the techniques discussed herein.

[0016]

[0022] Furthermore, in some examples, the techniques described herein may additionally or alternatively include determining estimated radar noise levels, object-specific radar response thresholds, and / or drivable / undrivable surfaces based on object detection and other sensor data received from additional or alternative sensor modalities (e.g., cameras, LiDAR sensors, etc.). In some examples, various techniques described herein (e.g., radar noise estimation of location in the environment, radar response threshold determination of object types, and threshold-based drivable / undrivable surface determination, etc.) may be performed in response to a determination that other vehicle sensors, such as cameras or LiDAR sensors, may be blocked or obscured by vapor, light flares, reflections, etc. Additionally or alternatively, the techniques described herein may be performed in a first operation, and thereafter any location determined to potentially conceal pedestrians (or other object types) may be provided for an additional operation using other sensor modalities to further analyze the location (e.g., visual object recognition and analysis, etc.).

[0017]

[0023] The technology described in the present specification for determining positions in radar data where objects may potentially be hidden may additionally or alternatively include receiving and / or determining radar response profiles (or response profiles) associated with various object types. A response profile may parameterize characteristics of an object type that affect how the object type influences radio waves, and thus how the object type "appears" in a radar sensor output signal. For example, a response profile may include received power and / or RCS associated with an object type. In some examples, the values of received power and / or RCS indicated by the response profile may be deterministic, or in additional or alternative examples, the values may be probabilistic (e.g., indicated by a probability distribution function associated with the object type). In some examples, a likelihood that an object will or will not be detected may be determined for one or more object types. For example, the technology may include determining a first likelihood that a pedestrian will not be detected at a particular position, a second likelihood that a large vehicle will not be detected at that position, a third likelihood that a small vehicle will not be detected, a fourth likelihood that a traffic sign will not be detected, and the like. In some examples, the technology may include storing response profiles related to object type, object size, object reflectance, and the like. In some examples, response profiles may be indexed by range, azimuth angle, and / or Doppler.

[0018]

[0024] In additional or alternative aspects, the present technology may comprise determining likelihoods associated with object types and portions of an environment (e.g., for different bins of range (or distance), azimuth, Doppler, and / or elevation). The present technology may comprise associating the likelihoods with portions of a radar spatial grid. For example, the radar spatial grid may comprise a plurality of cells, each of which may represent different portions of the environment and / or different bins of radar data. In some examples, a cell may have one or more likelihoods associated therewith, and each likelihood may be associated with a different object type.

[0019]

[0025] In some examples, an autonomous vehicle may generate a trajectory for controlling operation of the autonomous vehicle based at least in part on the radar spatial grid. The present technology may thereby improve the safety and effectiveness of operation of the autonomous vehicle. Furthermore, the techniques discussed herein may allow a computer to infer the presence of potential false negatives in radar data without requiring receipt of raw radar signals and / or without (proprietary) information about the algorithm by which a radar device generates detections.

[0020]

[0026] Figure 1 shows an exemplary scenario 100, which includes an autonomous vehicle 102 configured to determine drivable and non-drivable surfaces in an environment using radar response thresholds associated with objects. In some examples, the autonomous vehicle 102 may be an autonomous vehicle configured to operate according to a Level 5 classification issued by the U.S. Department of Transportation's National Highway Traffic Safety Administration, which describes a vehicle capable of performing all safety-critical functions for the entire journey in situations where a driver (or occupant) is not expected to control the vehicle at any time. However, in other examples, the autonomous vehicle 102 may be a fully or partially autonomous vehicle with other levels or classifications. In this specification, the technology is intended to be applicable to more than just robotic control, such as autonomous vehicles. For example, the technology discussed herein may be applied to airspace object detection, manufacturing, augmented reality, and so on. Furthermore, even though the autonomous vehicle 102 is represented as a land vehicle, in some examples, the autonomous vehicle 102 may be a spacecraft, a surface vessel, and / or something else.

[0021]

[0027] According to the technology discussed herein, an autonomous vehicle 102 may receive sensor data from its sensors 104. For example, sensors 104 may include position sensors (e.g., Global Positioning System (GPS) sensors), inertial sensors (e.g., accelerometers, gyroscopes, etc.), magnetic field sensors (e.g., compasses), position / velocity / acceleration sensors (e.g., speedometers, drive system sensors), depth position sensors (e.g., lidar sensors, radar sensors, sonar sensors, time-of-flight (ToF) cameras, depth cameras, and / or other depth-sensing sensors), image sensors (e.g., cameras), sound sensors (e.g., microphones), and / or environmental sensors (e.g., barometers, hygrometers, etc.).

[0022]

[0028] Sensor 104 can generate sensor data that can be received by a computing device 106 associated with the vehicle 102. However, in other examples, some or all of the sensors 104 and / or computing devices 106 may be isolated from the autonomous vehicle 102 and / or located remotely from the autonomous vehicle 102, and data capture, processing, commands and / or control may be communicated with the autonomous vehicle 102 by one or more remote computing devices via wired and / or wireless networks.

[0023]

[0029] Figure 1 shows an example of a radar device 108, which may be associated with an autonomous vehicle 102 and / or collect radar sensor data as the autonomous vehicle 102 moves through the environment. In some examples, the radar device 108 may have a field of view α that covers at least a portion of the environment surrounding the autonomous vehicle 102, i.e., a scan area. In various examples, the autonomous vehicle 102 may have any number of one or more radar devices and / or sensors (1, 2, 4, 5, 8, 10, etc.). In the illustrated example, the field of view α is expressed as a field of view of approximately 180 degrees. However, in other examples, the field of view of the radar sensor can be larger (e.g., 220 degrees, 270 degrees, 360 degrees) or smaller (e.g., 120 degrees, 90 degrees, 60 degrees, 45 degrees) than this angle. Furthermore, the autonomous vehicle 102 may include multiple radar sensors having multiple different fields of view, distances, scan rates, etc. In some examples, the autonomous vehicle 102 may include multiple radar sensors having at least partially overlapping fields of view so that the multiple radar sensors capture at least a portion of the environment in common.

[0024]

[0030] The computing device 106 may include a perception engine 110 configured to determine what is present in the environment surrounding the autonomous vehicle 102. Although not shown in Figure 1, the computing device 106 may also include a predictive component that includes the ability to generate predictive information associated with the environment, and a planning component that includes the ability to determine how the autonomous vehicle 102 should operate within the environment based on the information received from the perception engine 110. The perception engine 110 may include one or more machine learning (ML) models and / or other computer executable instructions for detecting, identifying, segmenting, classifying, and / or tracking objects from sensor data collected from the environment surrounding the autonomous vehicle 102. In some examples, the computing device 106 may also include a radar response threshold component 112, a radar noise estimator 114, and / or a threshold evaluation component 116. As will be described in more detail below, the radar response threshold component 112 may include the ability to determine a radar response threshold that can be applied by the autonomous vehicle 102 as it moves through the environment. The radar response threshold may be determined based on a vehicle safety metric, the radar response distribution of an object type, and / or a drivable surface metric, balancing the possibility that an object may be obscured by radar noise in the area of ​​radar data with the desirability for the autonomous vehicle 102 to determine a safe and efficient route through the environment. The radar noise estimator 114 may be configured to determine an estimate of radar noise (e.g., RCS noise and / or Doppler noise) based on object detection by the radar device 108 in the autonomous vehicle 102. The radar noise received by the radar device 108 may be based on the sidelobe level generated by an object reflecting the radar transmission signal. As will be described in more detail below, the radar noise near the target detection may be based on the distance difference between the target detection and the location, the Doppler difference between the target detection and the location, and the power (e.g., intensity) of the target detection.The threshold evaluation component 116 can evaluate radar response thresholds (e.g., RCS and / or Doppler thresholds) associated with specific types of objects (e.g., pedestrians, bicycles, animals, cars, etc.) against estimated radar noise levels in different regions of radar data to determine surfaces that the autonomous vehicle 102 can and cannot traverse.

[0025]

[0031] In some examples, computing device 106 may receive radar data from one or more radar devices 108. For example, a radar device may receive a return signal (e.g., radio waves reflected from an object) based on a transmitted signal and may determine an estimated noise level based at least in part on characteristics of the return signal, such as average intensity and / or average power. The characteristics of the return signal may depend on the hardware and / or software configuration of the radar device (e.g., on the type of CFAR algorithm used by the radar device). In some cases, the radar noise level may be expressed as a constant noise floor, but additional or alternative noise floor types are contemplated, as will be further described herein. In some examples, a radar device may output an object detection associated with a portion of the return signal that satisfies or exceeds the radar noise level. When outputting a return radar signal and / or object detection, the radar device may output positional data indicating the distance (e.g., range), azimuth (e.g., scan angle at which the object was detected), Doppler, elevation, received power (e.g., intensity and / or power of the return signal), SNR, and / or RCS associated with the detected object. In various examples, the perception engine 110 may receive radar data that may include object detection, and may or may not include data about the original signal from which the object detection was derived and / or the raw signal itself.

[0026]

[0032] Although the graphs and grids shown herein are presented as two-dimensional graphs and grids, the data they represent may be two-dimensional or more. For example, radar data and / or object detection may include one or more dimensions, such as received power, distance, azimuth (e.g., the scan angle at which the object was detected), Doppler, elevation, received power (e.g., the strength and / or power of the return signal), SNR, and / or RCS.

[0027]

[0033] In some examples, computing device 106 may additionally or alternatively receive image 118 from sensor 104. Image 118 illustrates an exemplary scenario in which a radar device may detect one or more targets and receive radar noise that potentially obscures additional objects from the detection of the return signal. Generally, the power intensity of the radar return signal may depend on the size, material, orientation, and / or surface angle of the object that reflects the radio waves and produces the return signal. Thus, larger objects such as vehicle 120 and truck 124 shown in image 118 may tend to produce larger return signals in the radar signal than smaller objects such as pedestrian 122. In some examples, larger return signals, such as those produced by vehicle 120 and / or truck 124, may skew the estimated noise level determined to be higher by the radar device due to the greater intensity of the return signal attributable to the larger object. Smaller objects within the same or similar area, such as pedestrian 122 (e.g., objects with weaker return signals), may not be detected by the radar device due to a distorted noise threshold. The proximity at which an undetected object will not be detected unless it approaches a larger, "skewing" object may depend on the technique used by the radar device to set the noise level. For example, if the estimated noise level is based on the area of ​​a cell, smaller objects within that area may not be detected, but if the estimated noise level is determined on a cell-by-cell basis, the likelihood of detecting smaller objects is slightly improved.

[0028]

[0034] In some examples, the computing device 106 may also include a radar response threshold component 112 configured to determine the radar response threshold of an autonomous vehicle 102 as it travels through an environment. In this example, the radar response threshold component 112 is implemented on the autonomous vehicle 102, but in other cases, the radar response threshold component 112 may be implemented on a separate computing device (e.g., computing device 938, described later). In such cases, the remote radar response threshold component 112 may use various techniques described herein to determine and transmit the radar response threshold used during driving operations to one or more autonomous vehicles 102. In yet another example, some parts of the radar response threshold component 112 may be implemented outside the autonomous vehicle 102 to determine a generalized data-driven radar response threshold, while other parts of the radar response threshold component 112 may be implemented on the autonomous vehicle 102 to customize or adjust the threshold to a specific environment, driving conditions, user preference, etc.

[0029]

[0035] The radar response threshold component 112 may use one or more data items from various different data sources to determine the radar response threshold applied by the autonomous vehicle 102. For example, as shown in this example, the radar response threshold component 112 may receive and use a vehicle safety metric 126 to determine the radar response threshold. The vehicle safety metric 126 may include one or a combination of minimum permissible driving safety criteria such as accident rate (e.g., collisions per mile driven), injury rate, vehicle or property damage rate, and estimated fatality rate. Other types of vehicle safety metrics 126 may include near-miss collision rate, speed limit or traffic violation rate, excessive braking or acceleration rate, comfort metric compliance rate, and / or any data associated with the performance of the autonomous vehicle 102. In some cases, the vehicle safety metric 126 may also be adjusted based on the amount of damage or injury that is likely to occur if a collision occurs. For example, the vehicle safety metric 126 may be modified upward or downward based on the current speed of the autonomous vehicle 102 and / or the type of object the vehicle may potentially collide with (e.g., pedestrians, bicycles, or cars, compared to traffic signs or mailboxes).

[0030]

[0036] When determining radar response thresholds using the vehicle safety metric 126, in some cases the radar response threshold component 112 may evaluate false negative and false positive detections (as well as true negatives and true positives) for several different possible thresholds. The radar response threshold component 112 may then select a threshold that minimizes the sum of false negatives and false positives, or otherwise provide an efficient balance between the possibility of failing to detect an object hidden by radar noise in a region of radar data (e.g., false negatives) and incorrectly determining that an object could be hidden when it does not exist in that region of the environment (e.g., false positives).

[0031]

[0037] In some examples, the radar response threshold component 112 may evaluate a particular radar response threshold by applying thresholds to various ground truth driving scenarios. Ground truth driving scenarios may be simulated scenarios, log-based scenarios, and / or live driving scenarios. To evaluate the radar response threshold, the radar response threshold component 112 may apply thresholds between one or more ground truth driving scenarios. The radar response threshold component 112 may determine, by applying thresholds to areas of radar data affected by radar noise from nearby object detection, whether the radar noise in that area is large enough to potentially obscure another object (e.g., positive object detection) or insufficient to obscure another object (e.g., negative object detection). The radar response threshold component 112 may then verify positive or negative object detections and confirm whether an object is present in the area using ground truth data, which may include data from other sensor means (e.g., Lidar or image data) or manually labeled or verified data. Based on positive or negative object determinations using radar response thresholds and corresponding verifications using ground verification data, the radar response threshold component 112 can identify whether a determination is true positive, true negative, false positive, or false negative. The radar response threshold component 112 can perform multiple such analyses on radar response thresholds in multiple different driving scenarios and combine the results to extrapolate to the number (or rate) of accidents, collisions, damage / injury, or other vehicle safety incidents. Thus, the radar response threshold component 112 can determine vehicle safety metrics associated with a particular radar response threshold, or conversely, determine radar response thresholds 132 to be applied by the autonomous vehicle 120 based on a provided target or desired vehicle safety metric 126.

[0032]

[0038] As described above, the radar response threshold component 112 may also use a radar response distribution 128 to determine a radar response threshold 132 for an autonomous vehicle 102 in some examples. The radar response distribution 128 may include a power distribution (e.g., an RCS distribution) and / or a Doppler distribution and may be associated with a specific object type (e.g., pedestrians, bicycles, cars, trucks, animals, etc.). Using one or more radar response distributions 128, the radar response threshold component 112 may determine a radar response threshold based on a desired probability of an object of an object type detected by the threshold (e.g., 95% for pedestrians).

[0033]

[0039] Additionally or alternatively, the radar response threshold component 112 may determine the radar response threshold 132 using a drivable surface metric 130. The drivable surface metric 130 may include the minimum amount and / or percentage of the area around the autonomous vehicle 102 that is designated as a drivable surface. For example, based on a given drivable surface metric 130 of 60%, the radar response threshold component 112 may determine a corresponding radar response threshold 132 that results in 60% of the area around the autonomous vehicle 102 (e.g., radar cells) being drivable.

[0034]

[0040] In some cases, the radar response threshold component 112 may determine the radar response threshold 132 of the autonomous vehicle 102 based on a combination and / or balance between a vehicle safety metric 126 and a drivable surface metric 130 to provide both a high level of vehicle safety and drivability through the environment. As described below, if a relatively large radar response threshold 132 is selected, the threshold evaluation component 116 may identify less area of ​​radar data as potentially obscuring objects within radar noise, and thus a larger overall drivable surface area may be achieved. Conversely, if a relatively small radar response threshold 132 is selected, the threshold evaluation component 116 may identify more area of ​​radar data as potentially obscuring objects, resulting in a smaller overall drivable surface area. In some cases, the radar response threshold component 112 may determine the largest radar response threshold 132 that conforms to a given vehicle safety metric 126, and the smallest radar response threshold 132 that conforms to a given drivable surface metric 130. In such cases, the radar response threshold component 112 may select a radar response threshold 132 between a determined minimum and maximum value to conform to both the desired vehicle safety metric 126 and the drivable surface metric 130.

[0035]

[0041] In some cases, a general radar response threshold may be determined by a remote computing system using the techniques described herein, or transmitted to an autonomous vehicle 102 and modified by the autonomous vehicle 102 based on the current driving environment. For example, the radar response threshold component 112 may determine a specific radar response threshold 132 by tuning a general radar response threshold upward or downward based on the current route, traffic conditions, time of day, the number of pedestrians (or other objects) in the environment, etc. Based on environmental conditions, the radar response threshold component 112 may determine that the radar response threshold should be decreased to improve vehicle safety in the current environment, or increased to increase the amount of drivable surface in the environment.

[0036]

[0042] Additionally or alternatively, the general radar response threshold may be adjusted upward or downward based on the current driving environment and / or driving conditions of the autonomous vehicle 102. For example, the radar response threshold component 112 may perform a first modification to the general radar response threshold when the autonomous vehicle 102 is driving in an urban area, and a second modification to the general radar response threshold when the autonomous vehicle 102 is driving may be in a less dense rural environment. The radar response threshold component 112 may also modify the general radar response threshold based on the detection that the autonomous vehicle 102 is driving in adverse weather conditions (e.g., rain, snow, fog). In some examples, the radar response threshold component 112 may also modify any vehicle safety metric 126 based on the current driving environment and / or driving conditions of the autonomous vehicle 102.

[0037]

[0043] The radar response threshold component 112 may also adjust the radar response threshold 132 upward or downward for a particular region, or apply different object-specific thresholds to the region based on the type of road surface in the region. For example, if a radar data region potentially affected by radar noise corresponds to a sidewalk, the radar response threshold component 112 may apply a radar response threshold 132 configured to detect pedestrians. Conversely, for different radar data regions corresponding to different surface types (e.g., bicycle lanes, driving or carpool lanes, etc.), the radar response threshold component 112 may apply different radar response thresholds 132 configured to detect different object types (e.g., bicycles, small cars, etc.).

[0038]

[0044] In some examples, the perception engine 110 may determine the probability (or confidence level) that a radar return signal associated with a particular location is true positive, false positive, true negative, or false negative. For example, to determine various probabilities of a return signal at a given location, the perception engine 110 may use a radar noise estimator 114 to determine an estimated noise floor, a threshold evaluation component 116 to determine a radar response threshold associated with a particular object type (e.g., a pedestrian), and at least partially based on the estimated noise floor and object type threshold, determine the probability of a hidden object at that location. The radar noise estimator 114 may determine one or more estimated noise levels at that location at least partially based on one or more object detections received from a radar device, and the radar response threshold component 112 may use a distribution associated with a particular object type to determine RCS and / or Doppler thresholds associated with the object type and / or different object parameters (e.g., size, estimated reflectivity).

[0039]

[0045] Based on the estimated noise level at a given location and radar response thresholds for various object types, the perception engine 110 may determine whether the location is sufficiently likely to contain an object of a particular object type (e.g., whether it meets or exceeds a probability threshold). In other words, based on the estimated radar noise and object type thresholds, the perception engine 110 may determine whether a radar device is capable of detecting an object of a particular object type within a specific region of the environment associated with a portion of the radar data. In some examples, a portion of the radar data may be defined as a bin or some other portion representing a portion of the environment. A bin may contain radar data associated with a set of distance, azimuth, elevation, and / or received power. For example, a particular bin may contain received power data associated with any object detection associated with a range of azimuth, distance, and / or elevation specified by the bin. In some examples, a bin may be associated with a cell in the radar spatial grid 134 and / or represented as a cell in the radar spatial grid 134, as described in detail below. In this example, a radar spatial grid 134 is used, but in other cases, radar data about the environment may be represented in other non-grid configurations such as radar cells or radar base contours. In some examples, bins may be associated with set constants and / or ranges of values ​​in one or more dimensions of the radar data. For example, bins may be associated with a constant elevation angle, a range of distances, a range of azimuth angles, and / or any Doppler value.

[0040]

[0046] The perception engine 110 may, additionally or alternatively, utilize sensor data captured by the sensor 104 to generate and maintain one or more spatial grids, including a radar spatial grid 134, which may contain cells associated with regions of the environment. Each cell in the radar spatial grid 134 may be associated with a bin (or other portion) of radar data. In some examples, the perception engine 110 may determine whether the radar data associated with a cell is likely to contain a hidden object and indicate whether the likelihood meets or exceeds a threshold associated with the object type. In some examples, cells in the radar spatial grid 134 may, alternatively or additionally, include a designation that they are occupied by an object (e.g., that at least one object detection has been output by a radar device or other system of the autonomous vehicle 102 in relation to the region of the environment corresponding to the cell), and / or additional metadata associated with such detections, such as other data determined by the perception engine 110, including semantic labels, rida points, rida instance segmentation, radar instance segmentation, etc., as described in more detail herein.

[0041]

[0047] In this example, the radar spatial grid 134 is shown as an 8x8 grid for simplification. However, in other examples, any size (e.g., the real-world region associated with the spatial grid), shape (e.g., the length and width of the spatial grid), and resolution (e.g., the size of the cells used to construct the spatial grid) may be used for the radar spatial grid 134, depending on the required accuracy and precision, bin size (dimensions), memory size constraints, processing speed and load constraints, sensor range limitations, etc. In some examples, the spatial grid may be sized and shaped to match the reliable range of the sensor 104 used to capture the sensor data into which the spatial grid is input, and the resolution may be selected to maximize the accuracy and precision required for a given application with memory and processing constraints. In some examples, the length and width may be the same, while in others, they may be different. In a specific example, the size of the spatial grid could be approximately 50-200 meters wide and 50-200 meters long, with a resolution of 0.25 meters per cell.

[0042]

[0048] In some examples, the perception engine 110 may additionally or alternatively determine the position of the autonomous vehicle 102 determined by a positioning engine (not shown) that can locate the autonomous vehicle 102 using any sensor data, data related to objects in the vicinity of the autonomous vehicle 102 (e.g., classifications, instance segmentations, and trajectories associated with detected objects), route data specifying the vehicle's destination, global map data identifying road features (e.g., features detectable in different sensor modalities useful for locating the autonomous vehicle), and local map data identifying features detected in close proximity to the vehicle (e.g., location, building, tree, fence, fire hydrant, stop sign location and / or size, and other features detectable in various sensor modalities). The data generated by the perception engine 110 (including the radar spatial grid 134) may be collectively referred to as “perceptual data.” Once the perception engine 110 generates perceptual data, it may provide the perceptual data to the prediction and / or planning components.

[0043]

[0049] The planning component within the computing device 106 may use perceptual data, including the radar spatial grid 134 and / or any determination of drivable and / or non-drivable surfaces as described herein, to locate the autonomous vehicle 102 on a global map and / or a local map (which may be additionally or alternatively achieved by a positioning component not shown), determine one or more trajectories, control the movement of the autonomous vehicle 102 to travel along a path or route, and / or otherwise control the operation of the autonomous vehicle 102, any such operation may be performed by various other components (for example, positioning may be performed by a positioning engine not shown). For example, the planning component may determine the path of the autonomous vehicle 102 from a first position to a second position, and may substantially simultaneously generate multiple potential trajectories to control the movement of the autonomous vehicle 102, following backward horizon techniques (e.g., 1 microsecond, half a second) and at least partially based on the radar space grid 134 (e.g., to avoid any detected objects and to incorporate the likelihood that objects may be obscured by radar noise and not detected by the radar device). For example, the radar space grid 134 includes vehicle detection radar data 136 corresponding to vehicle 120 and second vehicle detection radar data 138 corresponding to track 124. The perception engine 110 may analyze the radar data to determine estimated noise levels associated with positions on the radar space grid 134, radar response thresholds and probability thresholds associated with specific object types, determine drivable / non-drivable surfaces on the radar space grid 134, and from there the trajectory of the autonomous vehicle 102 may be generated. Figure 1 shows an example of such a trajectory, represented as arrows indicating direction of travel, velocity, and / or acceleration, but the trajectory itself may contain instructions for a PID controller, which can then activate the drive system of the autonomous vehicle 102.

[0044]

[0050] Figure 2 shows exemplary pedestrian RCS distribution 200 and exemplary pedestrian Doppler distribution 202. In this example, distributions 200 and 202 are associated with pedestrians, but additional RCS and Doppler distributions may be associated with other object types (e.g., bicycles, cars, trucks, animals, etc.). Distributions 200 and 202 may be generated by the autonomous vehicle 102 and / or generated by separate external computing devices and systems and transmitted to the autonomous vehicle 102 for use in determining object type-specific radar response thresholds. The data on which distributions 200 and 202 are based may include pedestrian data captured by the vehicle's radar device 108 and / or sensor 104 as it moves through the physical environment. For example, the vehicle may capture and store log data including radar response data from pedestrians in the environment and additional sensor data (e.g., camera and / or LIDAR data) used to verify that the radar return signals correspond to pedestrians.

[0045]

[0051] In this example, the pedestrian RCS distribution 200 may correspond to an approximately normal distribution (or a Gaussian distribution). However, in other examples, the pedestrian RCS distribution, or the RCS distribution of other object types, may correspond to any possible probability distribution function. Individual pedestrian RCS data points within distribution 200 may be based, for example, on the pedestrian's size, the surface material associated with the pedestrian (e.g., clothing material, color, reflectivity, etc.), the pedestrian's orientation relative to the radar device, and / or the angle of the pedestrian's surface that reflects the radio waves that produce the return signal.

[0046]

[0052] In this example, the pedestrian Doppler distribution 202 corresponds to a trimodal distribution. In this example, the trimodal distribution may represent a relatively large number of pedestrians moving away from the radar device, pedestrians moving towards the radar device, and pedestrians stationary relative to the radar device, all at walking speeds of approximately 2–4 m / s from the radar device. However, in other examples, the distribution 202 may correspond to a uniform distribution, a normal distribution, or any distribution that represents a probability distribution function based on pedestrian Doppler radar measurements. Individual pedestrian Doppler data points within the distribution 202 may be based on pedestrian speed and / or any other measurements captured by the Doppler radar device.

[0047]

[0053] Figure 3 shows an exemplary radar data analysis including the radar return signal corresponding to the number of object detections in the environment, and the estimated noise level. This example also shows the distribution 200 described above with reference to Figure 2, where probability values ​​and / or confidence levels are applied to the distribution to determine the radar response threshold associated with the object type. In this example, the pedestrian RCS distribution 200 includes shaded and unshaded regions and shows the pedestrian RCS threshold 302. The RCS threshold 302 may be based on the probability percentile (e.g., the 5th percentile) of the pedestrian RCS values ​​in the distribution 200. A 5% probability may indicate that 95% of pedestrians detected by the radar device 108 (e.g., the shaded region of the distribution 200) should have RCS values ​​that satisfy or exceed the RCS threshold 302.

[0048]

[0054] As described above, the perception engine 110 or other components of the autonomous vehicle 102 may select a probability percentile based on the desired safety standard and / or confidence level that the radar data area does not obscure pedestrians. They may also modify the probability value (e.g., 5%) to increase or decrease the value and adjust the corresponding RCS threshold 302 to improve the vehicle's safety and / or driving efficiency. For example, reducing the probability from 5% to 2% may result in a lower RCS threshold to ensure that 98% of pedestrians detected by the radar device 108 should have an RCS value that meets or exceeds the lower RCS threshold. This may result in a higher confidence level that the drivable radar data area does not obscure pedestrians, but may also result in a smaller drivable surface. Conversely, increasing the percentile value from 5% to 8% may result in a higher RCS threshold and a larger drivable surface, but may result in a lower confidence level that the drivable radar data area does not obscure pedestrians.

[0049]

[0055] This example illustrates determining a pedestrian RCS distribution 200 and an RCS threshold 302 using a desired probability or confidence level (e.g., 5%), but in other examples, a pedestrian Doppler distribution 202 may be used in a similar or identical manner to determine a pedestrian Doppler threshold. For example, in the exemplary Doppler distribution 202, a desired probability of 5% may result in a Doppler threshold of -4 m / s, meaning that 95% of observed pedestrians will have Doppler measurements that meet or exceed the threshold of -4 m / s. Pedestrian RCS and Doppler distributions 200 and / or 202 may also be used to determine a pedestrian RCS and / or Doppler range, either as an alternative to or in addition to RCS and Doppler threshold. For example, a desired confidence level of 95% for Doppler values ​​may correspond to a Doppler range between -3 m / s and 3 m / s. In various examples, ranges and / or thresholds of RCS and / or Doppler values ​​may be used to determine which surfaces are drivable and which are not.

[0050]

[0056] Furthermore, in some cases, if it is possible to determine the likely direction of movement of a pedestrian (or other object) in relation to the autonomous vehicle 102, the pedestrian Doppler distribution 202 can be modified. For example, the autonomous vehicle 102 may use various components and functions described herein (e.g., perception components, maps, localization components, etc.) to determine the vehicle's position in the current environment relative to nearby crosswalks, sidewalks, bicycle paths, unidirectional or bidirectional streets, or other features in the environment. The size, shape, angle, and orientation of these environmental features can be used to determine the likely direction of movement of a pedestrian, and the radar response threshold component 112 may use these directions to determine a modified pedestrian Doppler distribution 202 that reflects a more accurate Doppler distribution of a pedestrian moving in the determined direction / angle relative to the vehicle.

[0051]

[0057] Radar response thresholds for object types, including RCS thresholds and / or Doppler thresholds, can also be modified upward or downward during vehicle operation to improve vehicle safety and / or driving efficiency as needed. For example, a vehicle component may adjust the radar response thresholds used for one or more object types to change the drivable and non-drivable surfaces determined for the vehicle based on the thresholds. For instance, if the environment surrounding the vehicle does not contain enough drivable surfaces to allow the vehicle to move through the environment, the object type threshold component may increase the radar response threshold to increase the amount of drivable surface available to the vehicle. Conversely, if the environment contains more than enough drivable surfaces, the object type threshold component may increase one or more radar response thresholds to increase the confidence level that a potential object could not be obscured by radar noise in the environment.

[0052]

[0058] Figure 3 also shows Chart 304, which illustrates an example of received radar data. The radar data shown in Chart 304 includes received power level and distance data associated with the received radar data from an exemplary environment. In this example, Chart 304 includes an exemplary object detection 306 and an estimated radar noise level 308 based on the object detection 306. The estimated radar noise level 308 at a certain location (e.g., distance from the radar device) may be based at least in part on the distance difference between that location and the object detection 306, and the power level of the object detection 306. In some cases, the estimated radar noise level 308 may also be based on multiple object detections and / or other attributes of radar data from surrounding or nearby cells within the scanned area. Examples of various techniques for determining the estimated radar noise floor, which may be incorporated into an autonomous vehicle 102 to assist in determining the location of potentially hidden objects and determining drivable / non-drivable surfaces, can be found, for example, in U.S. Patent Application No. 16,407,139, filed on 8 May 2019 and titled “Radar False Negative Analysis,” which is incorporated herein by reference in its entirety for all purposes.

[0053]

[0059] Radar data chart 304 also includes two examples of radar return signals 310 and 312 representing pedestrians in the environment at locations relatively close to the object detection 306. As shown in chart 304, the radar data associated with object detection 306 overlaps with the radar data from radar return signals 310 and 312 in that radar data from different detections may affect the same / overlapping regions in the distance and / or Doppler dimensions. In this example, radar return signals 310 and 312 have the same signal power, which may be the same as the RCS threshold 302. The first pedestrian return signal 310 is at a location closer (in distance) to the object detection 306 and therefore may fall below the estimated radar noise level 308 and thus may not be detected by the perception engine 110 as a separate object detection. In contrast, a second pedestrian return signal 312 having the same power level but being further away (within distance) from the object detection 306 exceeds the estimated radar noise level 308 and can therefore be detected by the perception engine 110 as a separate object detection. Various pedestrian return signals can be dispersed at any RCS level within the distribution 200, but this example shows that the same pedestrian at the RCS threshold 302 may be detected or not detected based on the difference in distance between the pedestrian and the object detection 306. As described below, the point where the RCS threshold 302 intersects with the estimated radar noise level 308 may correspond to the boundary of a non-travelable surface surrounding the object detection 306.

[0054]

[0060] Figure 4 shows an exemplary grid map 400 illustrating the environment surrounding the autonomous vehicle 102. The exemplary grid map 400 may correspond to the image 118 described above with reference to Figure 1 and may represent the same environment surrounding the autonomous vehicle 102. The grid map 400 also includes grid lines corresponding to areas (e.g., grouping of one or more radar cells) and shaded areas indicating drivable and non-drivable areas within the environment. In this example, two non-drivable areas are shown corresponding to two vehicle radar detections 402 and 404. Vehicle radar detection 402 may correspond to vehicle detection radar data 136, and vehicle radar detection 404 may correspond to second vehicle detection radar data 138. In this example, the boundary between the black (non-drivable) area and the white (drivable) area may be where the estimated radar noise level intersects the radar response threshold associated with the object type. For example, if vehicle radar detection 402 corresponds to object detection 306 in Figure 3, the boundary of the non-drivable (blacked out) area in vehicle radar detection 402 may be the position where the estimated radar noise level 308 intersects with the pedestrian RCS threshold 302.

[0055]

[0061] As described above, different radar response thresholds, including the RCS threshold and / or Doppler threshold, may be associated with different object types. Thus, while the exemplary grid map 400 shows the boundary between drivable / immovable surfaces regarding the possibility of a hidden pedestrian in the radar data noise, in other examples, different sets of boundaries may be determined for different object types (e.g., bicycles, cars, trucks, animals, etc.). Thus, the perception engine 110 may determine multiple likelihoods for different object types in a single cell. The grid map 400 may have different drivable and immovable surfaces associated with a first object type (e.g., "pedestrian", "large vehicle", "passenger car", "cyclist", "four-legged animal"). The grid map 400 may additionally or alternatively include indications that individual cells in the grid map 400 corresponding to the position of the autonomous vehicle 102 in the surrounding environment are associated with estimated noise levels that either meet or do not meet thresholds specific to various object types, or are not associated with appropriate radar data (e.g., due to occlusion).

[0056]

[0062] Figure 5 shows Graph 500, which illustrates the difference (or delta) in range and Doppler measurements between the detection of a larger object 502 and two different object return signals (a first object return signal 504 and a second object return signal 506) corresponding to smaller objects in the environment. As mentioned above, a larger object with respect to radar data may refer to the magnitude of the radar return signal and not necessarily to the physical size of the object. Rather, the magnitude of the radar return signal may depend on a combination of the size, material, orientation, and / or surface angle of the object that reflects the radio waves and gives rise to the return signal. In this example, detection 502 may correspond to a larger object that can generate radar noise that can potentially mask nearby, smaller objects represented by the first object return signal 504 and the second object return signal 506.

[0057]

[0063] In some examples, at least a portion of the radar noise may correspond to the sidelobe level associated with the return signal of a larger object (e.g., detection 502). The sidelobe level associated with object detection may vary in various different patterns based on the characteristics of the radar device, radar signal, and detected object. However, the sidelobe level at a nearby location typically decreases in intensity as the location moves further away from the object detection location. Additionally, in some examples, the sidelobe level (and corresponding radar noise) associated with detection 502 of a larger object may be based on the difference in distance between detection 502 and the nearby location, and the difference in Doppler measurements between detection 502 and the nearby location. As shown in this example, the first object return signal 504 has a relatively small difference in distance from detection 502, but has a larger Doppler difference that can increase the amount of radar noise associated with the first object return signal 504. The second object return signal 506 has a relatively large difference in distance from the detection 502, as well as a large Doppler difference, which may result in a larger radar noise level associated with the second object return signal 506. Additionally, the Doppler measurement associated with the detection in the radar data may be determined in relation to the speed of the autonomous vehicle 102 when the Doppler measurement was captured.

[0058]

[0064] Figure 6 is a flowchart illustrating an exemplary process 600 for analyzing radar data to determine drivable and non-drivable surfaces for a vehicle moving through an environment. As described below, a vehicle may analyze radar data to determine noise levels in areas close to the vehicle based on object detection, and use radar response thresholds associated with specific object types and probability / confidence levels to determine drivable and non-drivable surfaces according to the various systems and techniques described herein. In various examples, the operation of process 600 may be carried out by one or more components of an autonomous vehicle, such as a perception engine 110 using a radar response threshold component 112, a radar noise estimator 114, a threshold evaluation component 116, and / or various other systems and components described herein.

[0059]

[0065] Process 600 is represented as a set of blocks in a logical flow diagram, which represent a sequence of operations, some or all of which can be implemented in hardware, software, or a combination thereof. In a software context, a block represents a computer-executable instruction stored in one or more computer-readable media that, when executed by one or more processors, performs the enumerated operations. Generally, computer-executable instructions include routines, programs, objects, components, encryption, decryption, compression, recording, data structures, etc., that perform a specific function or implement a specific abstract data type. The order in which the operations are described should not be interpreted as limiting. Any number of the listed blocks can be combined in any order and / or in parallel to execute a process or alternative process, and it is not necessary for all blocks to be executed. For illustrative purposes, the processes described herein are described with reference to the frameworks, architectures, and environments described in the examples herein, but processes can be implemented in a wide variety of other frameworks, architectures, or environments.

[0060]

[0066] In operation 602, the autonomous vehicle 102 may receive radar data from the radar device indicating the detection of one or more targets. The radar data may include several return signals received based on objects detected within the environment of the autonomous vehicle 102. The return signals, including radio waves reflected from the objects, may have various characteristics based on the characteristics of the detected object, such as distance, azimuth, elevation, Doppler value, received power, SNR, and / or RCS associated with the detected object. In various examples, the radar data received in operation 602 may include either raw radar signal data and / or return signal characteristics derived by the radar device 108 from the raw signal data.

[0061]

[0067] In operation 604, the autonomous vehicle 102 may determine the radar noise level in one or more areas of the environment based on the target detection in the radar data received in operation 602. In some examples, the perception engine 110 may use the radar noise estimator 114 to determine the estimated noise level (or noise floor) of an area in the environment based on the characteristics of nearby object detection. As described above with reference to Figure 3, if a larger object is detected at the detection location in the environment, the detection of the larger object may introduce noise into the radar data received for areas close to the detection location. For example, for a particular area of ​​the environment, the radar noise estimator 114 may determine the estimated noise level based on the distance difference between the particular area and the detection, the Doppler difference between the particular area and the detection, and the intensity and / or received power of the detection.

[0062]

[0068] In operation 606, the autonomous vehicle 102 may determine one or more radar response thresholds associated with a particular object type. As described above, the radar response thresholds may include RCS thresholds, Doppler thresholds, and / or other types of radar data thresholds associated with the radar data received in operation 602 (e.g., intensity or reflected power value thresholds). In some examples, the radar response threshold component 112 may determine the radar response thresholds using one or more distributions associated with a particular object type. For example, based on a predetermined probability or confidence level (e.g., 95%) for detecting pedestrians, the radar response threshold component 112 may use a pedestrian RCS distribution 200 to determine a pedestrian RCS threshold 302 applicable to detecting 95% of pedestrians that may be present in the environment. Similar techniques may be used to determine radar response thresholds corresponding to different probability / confidence levels (e.g., 90%, 95%, 99%), and different distributions (e.g., Doppler distribution 202) may be used to determine different radar response thresholds for different object types (e.g., Doppler threshold and / or distance). Additionally, as described above, the radar response threshold component 112 may determine different sets of radar response thresholds for different object types (e.g., pedestrians, bicycles, animals, small cars, traffic signs, etc.).

[0063]

[0069] In operation 608, the autonomous vehicle 102 determines whether the radar noise level for a particular area in the environment, determined in operation 604, satisfies or exceeds the radar response threshold for the object type, determined in operation 606. In some examples, the perception engine 110 may perform several comparisons between the radar noise levels determined by the radar noise estimator 114 for different areas in the environment and the radar response thresholds determined by the radar response threshold component 112 for one or more object types. If the estimated radar noise level for an area satisfies or exceeds the radar response threshold for the object type (608: Yes), then in operation 610, the perception engine 110 may determine that the area is a non-travelable surface. The determination in operation 610 that the area is non-travelable may correspond to a determination that the estimated noise level in the area is too high to be effectively scanned by the radar device, and that objects are not hidden in the area, with a desired level of confidence for a particular object type (e.g., 95% of pedestrians). In contrast, if the estimated radar noise level for the region does not exceed the radar response threshold for the object type (608: No), then in operation 612, the perception engine 110 may determine that the region is a traversable surface. The determination in operation 612 may correspond to a determination that the estimated noise level for the region is low enough to allow the perception engine 110 to conclude with a desired level of confidence that no object is hidden in the region for a particular object type (e.g., 95% of pedestrians).

[0064]

[0070] In operation 614, the perception engine 110 may determine the trajectory of the autonomous vehicle 102 and / or activate or deactivate additional features (e.g., CAS, remote control, autonomous driving functions) in order to control the autonomous vehicle 102, based on the determination of drivable and non-drivable areas in the environment. In some examples, the perception engine 110 (and / or a prediction or planning component) may use a map of drivable and non-drivable areas in the environment to determine a planning corridor for navigating the autonomous vehicle. For example, the planning corridor may be determined at least in part on the width and / or perception data of the autonomous vehicle received from the perception engine 110 (e.g., a grid map 400 that identifies drivable and non-drivable surfaces). In some examples, the planning corridor may combine potential trajectories generated by the computing device 106, select a trajectory from the potential trajectories to operate the autonomous vehicle 102, exclude non-drivable surfaces, and include drivable surfaces in the grid map 400. The planned route may, additionally or alternatively, be based at least in part on the vehicle width and / or tolerance associated with operating the autonomous vehicle 102.

[0065]

[0071] Figure 7 shows a radar data model 700 that stores estimated radar noise levels associated with the probabilities of different Doppler ranges in different regions of the environment. In this example, the radar data model 700 is a multidimensional model that stores multiple estimated radar noise levels for each region of the environment. In this example, a region may correspond to one or more radar cells and may be represented by the intersection of azimuth and distance values. In other examples, a region may include one or more additional parameters or dimensions (e.g., elevation) in place of or in addition to the azimuth and distance values.

[0066]

[0072] As described above, the sidelobe level (and corresponding radar noise) generated by the detection of large objects in the environment may be based on the distance difference and Doppler difference between the area of ​​object detection and the area where the radar noise estimate is determined. As a result, a single area 702 in the environment (defined by the intersection of distance and azimuth) may have different estimated noise levels based on Doppler measurements of objects (e.g., pedestrians) that may potentially be present in area 702. In some examples, the radar noise estimator 114 may determine different estimated radar noise levels for areas corresponding to different Doppler values. As shown in the radar data model 700, each area in the environment may have multiple different Doppler values ​​(or ranges of Doppler values). For example, for region 702, the model may define several Doppler values ​​704, 706, 708, 710, 712, and 714 based on the pedestrian Doppler distribution 202, which may include separate radar noise levels (e.g., RCS noise) associated with each of the different Doppler values ​​704-714. For illustrative purposes, in region 702, the radar noise estimator 114 may determine a first radar noise level value associated with Doppler value 704 (e.g., between -6 m / s and -4 m / s), a second radar noise level value associated with Doppler value 706 (e.g., between -4 m / s and -2 m / s), a third radar noise level value associated with Doppler value 708 (e.g., between -2 m / s and 0 m / s), and so on.

[0067]

[0073] In this example, to determine the overall RCS threshold associated with region 702, the threshold evaluation component 116 may use the individual radar noise level values ​​associated with different Doppler values ​​704-714, along with the probabilities associated with those different Doppler values ​​704-714 (for example, based on the pedestrian Doppler distribution 202). For example, the probability function used to determine the RCS threshold of region 702 based on the individual RCS thresholds associated with different Doppler values ​​corresponds to a 95% confidence level that no pedestrians are hidden in the region, and is expressed as follows according to Equation 1.

[0068] [Math]

[0069] In this example, each P(vel=N m / s) represents the probability that a pedestrian moves at N m / s in the environment, and each P(RCS<est RCS noise level at -N m / s) represents the probability that a specific RCS is smaller than an estimated radar noise level value (e.g., N m / s) associated with the same Doppler measurement. Using Equation 1, the threshold evaluation component 116 can solve to determine, for RCS, an RCS threshold corresponding to a desired probability / confidence level (e.g., 95%) that a pedestrian cannot hide in the region. Alternatively, Equation 1 may be performed using a given RCS term to solve for an overall probability associated with the same given RCS threshold, which in this example may be greater than or less than 0.95.

[0070]

[0074] FIG. 8 is a flow diagram illustrating another example process 800 for analyzing radar data to determine drivable and non-drivable surfaces for a vehicle traveling through an environment. In some examples, process 800 may be similar or identical to process 600 described above. However, in this example, a single region may have a plurality of different estimated radar noise levels associated with different Doppler values (or ranges of Doppler values), and the vehicle may determine individual probabilities associated with the different Doppler values, and sum the individual probabilities to determine an overall probability associated with the region. As described below, the operations of process 800 may be performed by one or more components of autonomous vehicle 102, such as radar response threshold component 112, radar noise estimator 114, threshold evaluation component 116, and / or perception engine 110 using various other systems and components described herein.

[0071]

[0075] In operation 802, the autonomous vehicle 102 may receive radar data from the radar device indicating the detection of one or more targets. In some examples, operation 802 may be similar to or identical to operation 602 described above, in which the radar data may include one or more return signals received based on objects detected in the environment of the autonomous vehicle 102.

[0072]

[0076] In operation 804, the autonomous vehicle 102 may determine an area in the environment, and radar data is analyzed to determine whether the area is a drivable or non-drivable surface. The area may be defined by the intersection of distance values ​​and azimuth values ​​(and / or elevation values) relative to the radar device 108. In some examples, the determined area may be the neighborhood of one or more radar target detections received in operation 802.

[0073]

[0077] In operation 806, the autonomous vehicle 102 may determine a set of Doppler probabilities for an object type (e.g., a pedestrian) and the corresponding estimated radar noise level associated with that Doppler probability. For example, as described above with reference to Figure 7, a pedestrian or other object type may be associated with different ranges of Doppler values ​​(e.g., -5 m / s to 5 m / s) and each Doppler value may have a different probability associated with it. These probabilities may be determined based on the pedestrian Doppler distribution 202 for pedestrians, or for different Doppler distributions associated with different object types. Additionally, since individual different Doppler values ​​may have different associated radar noise levels, the threshold evaluation component 116 may perform different probability evaluations using different RSC thresholds for individual different Doppler values.

[0074]

[0078] In operation 808, the threshold evaluation component 116 may determine different Doppler values ​​(or ranges of Doppler values) associated with an object type, and the estimated radar noise level associated with each Doppler value in a region. In operation 810, the threshold evaluation component 116 may evaluate the probability that an object of a particular object type (e.g., a pedestrian) will be obscured by estimated radar noise in a region of a particular Doppler value for the object. For example, the probability determination in operation 810 may represent the probability that a pedestrian moving at N m / s will be obscured by radar noise associated with the N m / s Doppler value. Thus, in operation 810, the threshold evaluation component 116 may use the pedestrian Doppler distribution 202 to determine the probability that pedestrians present in the region will be obscured by the radar noise level associated with the N m / s Doppler value (e.g., corresponding to the proportion of pedestrians with an RCS smaller than the radar noise level), and multiply that probability by the probability that pedestrians present in the region are moving at the N m / s Doppler value. As shown in this example and in Equation 1 above, the decision in operation 810 may be performed iteratively for each of the different Doppler values ​​that an object (e.g., a pedestrian) may potentially be present in the area.

[0075]

[0079] In operation 812, the threshold evaluation component 116 may determine the total probability that a pedestrian will be obscured by radar noise in that area by summing the individual probabilities that a pedestrian will be obscured by radar noise at a particular Doppler value across all different Doppler values ​​associated with the object. Equation 1 provides an example of a sum of probabilities that may be similar to or identical to the sum in operation 812.

[0076]

[0080] In operation 814, the autonomous vehicle 102 determines whether the total probability determined in operation 812 (e.g., the probability that an object will be obscured by radar noise in the area) is greater than a predetermined probability / confidence level associated with the object type. For example, a predetermined probability of 5% may represent a 95% confidence level that a pedestrian in the area will be detected in the radar data. In some examples, the comparison in operation 814 may be similar to or identical to the comparison in operation 608 described above. In this example, if the probability that a pedestrian present in the area will be obscured by radar noise satisfies or exceeds a predetermined probability for the pedestrian (814: Yes), then in operation 816, the perception engine 110 may determine that the area is a non-drivable surface. As described above, the decision in operation 816 that the area is not traversable may correspond to a decision that the estimated noise level in the area (e.g., across different Doppler values / ranges) is too high to allow the radar device to effectively scan the area, thus guaranteeing with a desired level of confidence that objects are not obscured by the area for a particular object type (e.g., 95% of pedestrians). Conversely, if the probability that pedestrians present in the area will be obscured by radar noise does not exceed a predetermined probability for pedestrians (814: No), then in operation 818, the perception engine 110 may determine that the area is a traversable surface. The decision in operation 818 may correspond to a decision that the estimated noise level in the area (e.g., across different Doppler values) is low enough to allow the perception engine 110 to conclude with a desired level of confidence that objects are not obscured by the area for a particular object type (e.g., 95% of pedestrians).

[0077]

[0081] In some cases, during or after operations 816 and 818, the perception engine 110 may determine the trajectory of the autonomous vehicle 102 and / or activate or deactivate additional features (e.g., CAS, remote control, autonomous driving functions, etc.) to control the autonomous vehicle 102. For example, the perception engine 110 may control the autonomous vehicle based on the determination of drivable and non-drivable areas in the environment, using techniques similar to or identical to the techniques of operation 614. Additionally, while the specific examples described above relate to determining the probability that a pedestrian will be obscured by the radar noise level in an area, in other examples, similar or identical techniques may be used to determine the probabilities of different object types. For example, the perception engine 110 may determine different grid maps with different drivable and non-drivable surfaces defined for different object types.

[0078]

[0082] Figure 9 shows a block diagram of an exemplary system 900 for implementing the technology described herein. In at least one example, the system 900 may include a vehicle 902, which may correspond to an autonomous or semi-autonomous vehicle configured to perform object perception and prediction functions, path planning and / or optimization. As described below, the vehicle 902 may include components configured to analyze radar detection to detect objects potentially hidden within radar noise. For example, the vehicle 902 may be similar to or identical to the autonomous vehicle 102 described above and may include components similar to or identical to the perception engine 110, prediction and / or planning components, radar response threshold component 112, radar noise estimator 114 and / or threshold evaluation component 116. The exemplary vehicle 902 could be a driverless vehicle, such as an autonomous vehicle configured to operate according to the Level 5 classification issued by the U.S. Department of Transportation's National Highway Traffic Safety Administration, which describes a vehicle capable of performing all safety-critical functions for the entire journey in a situation where the driver (or occupant) is not expected to control the vehicle at any time. In such an example, vehicle 902 can be configured to control all functions from the start to the completion of the journey, including all parking functions, and therefore does not require a driver and / or controls for driving vehicle 902, such as a steering wheel, accelerator pedal and / or brake pedal. This is merely an example, and the systems and methods described herein can be incorporated into any ground-based, air-based, or water-based vehicle, ranging from vehicles that require manual control by a driver at any time to vehicles that are partially or fully autonomously controlled.

[0079]

[0083] In this example, the vehicle 902 may include a vehicle computing device 904, one or more sensor systems 906, one or more emitters 908, one or more communication connections 910, at least one direct connection 912, and one or more drive systems 914.

[0080]

[0084] The vehicle computing device 904 may include one or more processors 916 and a memory 918 communicably coupled to one or more processors 916. In the illustrated example, the vehicle 902 is an autonomous vehicle, but the vehicle 902 may be other types of vehicles or robotic platforms. In the illustrated example, the memory 918 of the vehicle computing device 904 stores a positioning component 920, a perception component 922, a radar response threshold component 924, a radar noise estimator 925, a threshold evaluation component 926, one or more maps 928, one or more system controllers 930, a prediction component 932, and a planning component 934. Although shown in Figure 9 as existing in memory 918 for illustrative purposes, one or more of the localization component 920, perception component 922, radar response threshold component 924, radar noise estimator 925, threshold evaluation component 926, map 928, system controller 930, prediction component 932, and planning component 934 may be additionally or alternatively accessible to the vehicle 902 (for example, stored in memory away from the vehicle 902, or otherwise in memory accessible by the vehicle 902).

[0081]

[0085] In at least one example, the positioning component 920 may include the ability to receive data from the sensor system 906 to determine the position and / or orientation of the vehicle 902 (e.g., one or more of x-, y-, z-position, roll, pitch, or yaw). For example, the positioning component 920 may include and / or request / receive a map of the environment and continuously determine the position and / or orientation of the autonomous vehicle within the map. In some examples, the positioning component 920 may receive image data, LiDAR data, radar data, time-of-flight data, IMU data, GPS data, wheel encoder data, etc., using SLAM (Simultaneous Localization and Mapping), CLAMS (Simultaneous Calibration, Localization and Mapping), relative SLAM, bundle adjustment, nonlinear least-squares optimization, etc., to accurately determine the position of the autonomous vehicle. In some examples, the positioning component 920 can provide data to various components of the vehicle 902 for determining the initial position of the autonomous vehicle, as discussed herein, to generate a trajectory, and / or to determine that an object is in proximity to one or more crosswalk areas, and / or to identify candidate reference lines.

[0082]

[0086] In some examples, the perception component 922 may include functions for performing object detection, segmentation, and / or classification. In some examples, the perception component 922 may be similar to or identical to the perception engine 110 and may provide processed sensor data indicating the presence of entities in proximity to the vehicle 902 and / or the classification of entities as types of entities (e.g., cars, pedestrians, bicycles, animals, buildings, trees, road surfaces, curbs, sidewalks, stop signals, stop signs, unknowns, etc.). In additional or alternative examples, the perception component 922 may provide processed sensor data indicating detected entities (e.g., tracked objects) and / or one or more characteristics associated with the environment in which the entities are located. In some examples, the properties associated with an entity may include, but are not limited to, x-position (global and / or local position), y-position (global and / or local position), z-position (global and / or local position), orientation (e.g., roll, pitch, yaw), entity type (e.g., classification), entity velocity, entity acceleration, and entity range (size). Properties associated with an environment may include, but are not limited to, the presence of other entities in the environment, the state of other entities in the environment, time of day, day of the week, season, weather conditions, and brightness / darkness indicators.

[0083]

[0087] As shown in this example, the perception component 922 may include a radar response threshold component 924, a radar noise estimator 925, and / or a threshold evaluation component 926. The radar response threshold component 924, the radar noise estimator 925, and the threshold evaluation component 926 may perform similar or identical functions to the radar response threshold component 112, the radar noise estimator 114, and the threshold evaluation component 116 described above. For example, the radar response threshold component 924 may be configured to determine a radar response threshold that can be applied by the autonomous vehicle 902 while operating in a driving environment. The radar noise estimator 925 may be configured to determine an estimate of radar noise (e.g., RCS noise and / or Doppler noise) based on the detection of objects by one or more radar devices on the vehicle 902. As described above, the radar noise may be based on the sidelobe level received in response to the radar transmission signal. Radar noise at a location close to the target detection may be based on the range difference between the target detection and the location, the Doppler difference between the target detection and the location, and the power (e.g., intensity) of the target detection. The threshold evaluation component 926 may determine and / or store radar response thresholds (e.g., RCS and / or Doppler thresholds) associated with a particular type of object (e.g., pedestrians, bicycles, animals, cars, etc.). As described above, object-type specific thresholds for radar responses can be based on object-specific RCS and Doppler distributions and can be adjusted based on a desired probability that the location does not contain hidden objects of the object type. The perception component 922 may include the ability to modify and adjust thresholds and compare them to estimated radar noise at various locations to determine drivable and / or impedimentable surfaces around the vehicle 902. As shown in this example, the radar response threshold component 924, radar noise estimator 925, and / or threshold evaluation component 926 may be implemented within the perception component 922.However, in other examples, one or more of the radar response threshold component 924, the radar noise estimator 925, and / or the threshold evaluation component 926 may be implemented within the prediction component 932, the planning component 934, or other parts within the vehicle computing device 904.

[0084]

[0088] Memory 918 may further include one or more maps 928 that can be used by a vehicle 902 to navigate within the environment. For the purposes of this disclosure, a map may be any number of data structures modeled in two, three, or N dimensions that can provide information about the environment, such as topology (intersections, etc.), roads, mountain ranges, terrain, and the environment in general. In some examples, a map may include, but is not limited to, texture information (e.g., color information (e.g., RGB color information, Lab color information, HSV / HSL color information), intensity information (e.g., Lider information, radar information, etc.), spatial information (e.g., vectorized information about the features of the environment, image data projected onto a mesh, individual "surfaces" (e.g., polygons associated with individual colors and / or intensities)), and reflectance information (e.g., specular reflectance information, retroreflectance information, BRDF information, BSSRDF information, etc.). In one example, a map may include a three-dimensional mesh of the environment. In some examples, maps can be stored in a tiled format, where individual tiles of the map represent discrete parts of the environment, and can be loaded into working memory as needed. In at least one example, one or more maps 928 can contain at least one map (e.g., an image and / or a mesh).

[0085]

[0089] In some examples, the vehicle 902 can be controlled at least partially based on the map 928. That is, the map 928 can be used in conjunction with a localization component 920, a perception component 922, a prediction component 932, and / or a planning component 934 to determine the location of the vehicle 902, identify objects in the environment, and / or generate a path and / or trajectory for navigating through the environment.

[0086]

[0090] In some examples, one or more maps 928 can be stored on a remote computing device, such as in the memory 942 of a computing device 938, and can be accessed via the network 936 to the vehicle 902. In some examples, multiple maps 928 can be retrieved from memory 942 and can be stored based on characteristics, for example, entity type, time, day of the week, season, etc. Storing multiple maps 928 can have similar memory requirements, but can increase the speed at which data in the maps can be accessed.

[0087]

[0091] In at least one example, the vehicle computing device 904 may include one or more system controllers 930 which can be configured to control the steering, propulsion, braking, safety, emitter, communication, and other systems of the vehicle 902. These system controllers 930 may communicate with and / or control corresponding systems of the drive system 914 and / or other components of the vehicle 902. For example, a planning component 934 may generate instructions based at least in part on perceptual data generated by a perception component 922 (which may include either a radar spatial grid and / or likelihood as discussed herein), transmit the instructions to a system controller 930, and the system controller 930 may control the operation of the vehicle 902 based at least in part on the instructions. In some cases, if the planning component 934 receives notification that tracking of an object has been "lost" (for example, the object is visible in the LIDAR but no longer appears in sensor data that is not obstructed by other objects), the planning component 934 may generate instructions to bring the vehicle 902 to a safe stop and / or send a request for remote operation assistance.

[0088]

[0092] In general, the prediction component 932 may include the ability to generate predictive information associated with objects in the environment. For example, the prediction component 932 may be implemented to predict the position of a pedestrian approaching a crosswalk area (or otherwise, an area or location associated with a pedestrian crossing the road) in the environment when crossing the crosswalk area or preparing to cross it. As another example, the technology discussed herein may be implemented to predict the positions of other objects (e.g., vehicles, bicycles, pedestrians, etc.) as a vehicle 902 moves through the environment. In some examples, the prediction component 932 may generate one or more predicted positions, predicted speeds, predicted trajectories, etc., for a target object based on the attributes of the target object and / or other objects adjacent to the target object.

[0089]

[0093] In general, the planning component 934 is capable of determining the path that the vehicle 902 will follow to move through the environment. The planning component 934 is capable of determining various routes and trajectories, and various levels of detail. For example, the planning component 934 is capable of determining a route to travel from a first location (e.g., current location) to a second location (e.g., target location). For the purposes of this discussion, the route may be a sequence of waypoints for moving between the two locations. In non-limiting examples, waypoints may include streets, intersections, Global Positioning System (GPS) coordinates, etc. Furthermore, the planning component 934 is capable of generating instructions for guiding the autonomous vehicle along at least a portion of the route from the first location to the second location. In at least one example, the planning component 934 is capable of determining how to guide the autonomous vehicle from a first waypoint in a sequence of waypoints to a second waypoint in a sequence of waypoints. In some examples, the instructions may be a trajectory or a portion of a trajectory. In some cases, multiple tracks can be generated substantially simultaneously (e.g., within technical limits) according to the reverse horizon technique, and one of the multiple tracks is selected to navigate vehicle 902.

[0090]

[0094] In some examples, the planning component 934 can generate one or more trajectories for the vehicle 902 based at least partially on predicted positions associated with objects in the environment. In some examples, the planning component 934 can evaluate one or more trajectories for the vehicle 902 using time logic such as linear time logic and / or signal time logic.

[0091]

[0095] For ease of understanding, the components discussed herein (e.g., the localization component 920, the perception component 922, one or more maps 928, one or more system controllers 930, the prediction component 932, and the planning component 934) are described as being separated for illustrative purposes. However, operations performed by various components can be combined or performed by any component. Furthermore, any component described as being implemented in software can be implemented in hardware, and vice versa. Moreover, any function implemented in the vehicle 902 can be implemented in the computing device 938 or other components (and vice versa).

[0092]

[0096] In at least one example, the sensor system 906 may include time-of-flight sensors, lidar sensors, radar devices and / or radar sensors, ultrasonic transducers, sonar sensors, position sensors (e.g., GPS, compass, etc.), inertial sensors (e.g., inertial measuring unit (IMU), accelerometer, magnetometer, gyroscope, etc.), cameras (RGB, IR, intensity, depth, etc.), microphones, wheel encoders, environmental sensors (temperature sensors, humidity sensors, light sensors, pressure sensors, etc.), and the like. The sensor system 906 may include multiple instances of each of these sensors or other types of sensors. For example, the time-of-flight sensors may include individual time-of-flight sensors positioned at the corners, front, back, sides, and / or top of the vehicle 902. In another example, the camera sensors may include multiple cameras positioned at various locations on the exterior and / or interior of the vehicle 902. The sensor system 906 may provide input to the vehicle computing device 904. Additionally or alternatively, the sensor system 906 can transmit sensor data to one or more computing devices 938 via one or more networks 936 at a specific frequency, after a predetermined period of time, or in near real-time.

[0093]

[0097] Vehicle 902 may also include one or more emitters 908 that emit light and / or sound, as described above. In this example, the emitters 908 include internal audio and visual emitters that communicate with passengers of vehicle 902. For illustrative purposes only and not limited to, internal emitters may include speakers, lights, signs, display screens, touchscreens, haptic emitters (e.g., vibration and / or force feedback), mechanical actuators (e.g., seat belt tensioners, seat positioners, headrest positioners, etc.). In this example, emitters 908 may also include external emitters. For illustrative purposes only and not limited to, external emitters in this example include lights that indicate the direction of movement or other indicators of vehicle action (e.g., indicator lights, signs, light arrays, etc.), as well as one or more audio emitters (e.g., speakers, speaker arrays, horns, etc.) for audible communication with pedestrians or other nearby vehicles, one or more of which include acoustic beam steering technology.

[0094]

[0098] The vehicle 902 may also include one or more communication connections 910 that enable communication between the vehicle 902 and one or more other local or remote computing devices. For example, the communication connections 910 may facilitate communication between the vehicle 902 and / or other local computing devices on the drive system 914. The communication connections 910 may also allow the vehicle to communicate with other nearby computing devices (e.g., other nearby vehicles, traffic lights, etc.). The communication connections 910 may also enable the vehicle 902 to communicate with remotely operated computing devices or other remote services.

[0095]

[0099] The communication connection 910 may include physical and / or logical interfaces for connecting the vehicle computing device 904 to other computing devices or to a network such as the network 936. For example, the communication connection 910 may enable Wi-Fi®-based communication such as via frequencies defined by the IEEE 802.11 standard, short-range radio frequencies such as Bluetooth®, cellular communication (e.g., 2G, 3G, 4G, 4G LTE, 5G, etc.), or any suitable wired or wireless communication protocol that enables each computing device to interface with other computing devices.

[0096]

[0100] In at least one example, the vehicle 902 may include one or more drive systems 914. The vehicle 902 may have a single drive system 914 or multiple drive systems 914. In at least one example, if the vehicle 902 has multiple drive systems 914, the individual drive systems 914 may be located at opposing ends of the vehicle 902 (e.g., front and rear). In at least one example, the drive system 914 may include one or more sensor systems for detecting the conditions around the drive system 914 and / or the vehicle 902. For illustrative purposes only and not limiting, the sensor systems may include one or more wheel encoders (e.g., rotary encoders) for sensing the rotation of the wheels of the drive module, inertial sensors (e.g., inertial measuring units, accelerometers, gyroscopes, magnetometers, etc.) for measuring the orientation and acceleration of the drive module, cameras or other image sensors, ultrasonic sensors, lidar sensors, radar sensors, etc. for acoustically detecting objects around the drive system. Some sensors, such as wheel encoders, may be specific to the drive system 914. In some cases, the sensor system on the drive system 914 can overlap with or complement the corresponding system on the vehicle 902 (for example, the sensor system 906).

[0097]

[0101] The drive system 914 may include a high-voltage battery, a motor to propel the vehicle, an inverter to convert DC from the battery to AC for use by other vehicle systems, a steering system including a steering motor and steering rack (which may be electric), a braking system including hydraulic or electric actuators, a suspension system including hydraulic and / or pneumatic components, a stability control system for distributing braking force to mitigate traction loss and maintain control, an HVAC system, lights (e.g., headlights / taillights illuminating the exterior of the vehicle), and one or more other systems (e.g., other electrical components such as a cooling system, safety systems, on-board charging system, DC / DC converter, high-voltage junction, high-voltage cable, charging system, and charging port). Additionally, the drive system 914 may include a drive system controller capable of receiving and preprocessing data from sensor systems to control the operation of various vehicle systems. In some examples, the drive system controller may include one or more processors and a memory communicatively coupled to one or more processors. The memory may store one or more components for performing various functions of the drive system 914. Furthermore, the drive system 914 may also include one or more communication connections that enable each drive system to communicate with one or more other local or remote computing devices.

[0098]

[0102] In at least one example, the direct connection 912 can provide a physical interface for coupling one or more drive systems 914 to the body of the vehicle 902. For example, the direct connection 912 can allow the transmission of energy, fluids, air, data, etc., between the drive system 914 and the vehicle. In some examples, the direct connection 912 can removably fix the drive system 914 to the body of the vehicle 902.

[0099]

[0103] In at least one example, the localization component 920, the perception component 922, the radar response threshold component 924, the radar noise estimator 925, the threshold evaluation component 926, one or more maps 928, one or more system controllers 930, the prediction component 932, and the planning component 934 are capable of processing sensor data as described above and transmitting their respective outputs to one or more computing devices 938 via one or more networks 936. In at least one example, the output of each component is capable of being transmitted to one or more computing devices 938 at a specific frequency, after a predetermined period, near real time, etc. Additionally or alternatively, the vehicle 902 is capable of transmitting sensor data, including raw sensor data, processed sensor data, and / or representations of sensor data, to one or more computing devices 938 via the network 936. Such sensor data is capable of being transmitted to the computing devices 938 as one or more log files at a specific frequency, after a predetermined period, near real time, etc.

[0100]

[0104] The computing device 938 may include a processor 940 and a memory 942 for storing one or more radar response object profiles 944 and / or vehicle safety metrics 946. As described above, the radar response object profile 944 may include response data (e.g., RSC data and / or Doppler data) associated with various different object types (e.g., pedestrians, bicycles, animals, cars, etc.). The radar response object profile 944 may include individual values, distributions, and / or probability or confidence metrics associated with different object types. The vehicle safety metrics 946 may include collision and safety metrics such as miles per collision, injury or mortality estimates. In various examples, the computing device 938 may implement one or more heuristic-based systems and / or neural network models to determine the radar response object profile 944 based on the vehicle safety metrics 946 and / or log data received from vehicle 902 and / or additional vehicles operating in the environment. Additionally, any features or functions described in relation to the radar response threshold component 924, the radar noise estimator 925 (e.g., determining estimated radar noise based on radar detection), and / or the threshold evaluation component 926 (e.g., determining object type-specific probabilities and thresholds) may be implemented using heuristic-based techniques and / or neural network models and algorithms. In this example, the neural network is an algorithm that passes input data through a series of connected layers to produce an output. Individual layers of the neural network can constitute other neural networks, and any number of layers (whether convolutional or not) can be constituted. As can be understood in the context of this disclosure, the neural network can utilize machine learning, which can refer to a broad class of algorithms such that an output is produced based on trained parameters. Any type of machine learning can be used in accordance with this disclosure.

[0101]

[0105] The processor 916 of vehicle 902 and the processor 940 of computing device 938 can be any suitable processor capable of processing data and executing instructions for performing operations, as described herein. For illustrative purposes only and not limiting, processors 916 and 940 can include one or more central processing units (CPUs), graphics processing units (GPUs), or any other device or part of a device that processes electronic data and converts such electronic data into other electronic data that can be stored in registers and / or memory. In some examples, integrated circuits (e.g., ASICs), gate arrays (e.g., FPGAs), and other hardware devices can also be considered processors insofar as they are configured to implement encoded instructions.

[0102]

[0106] Memory 918 and 942 are examples of non-temporary computer-readable media. Memory 918 and 942 are capable of storing data for implementing the operating system and one or more software applications, instructions, programs, and / or functions resulting from the methods and various systems described herein. In various implementations, the memory can be implemented using any suitable memory technology, such as static random-access memory (SRAM), synchronous dynamic RAM (SDRAM), non-volatile / flash memory, or any other type of memory capable of storing information. The architectures, systems, and individual elements described herein may include many other logical, programmatic, and physical components, of which those shown in the accompanying drawings are merely illustrative examples relevant to the discussion herein.

[0103]

[0107] Although Figure 9 is shown as a distributed system, it should be noted that in alternative examples, components of vehicle 902 can be associated with computing device 938, and / or components of computing device 938 can be associated with vehicle 902. That is, vehicle 902 can perform one or more functions associated with computing device 938, and vice versa.

[0104] Exemplary section

[0108] A. A system comprising one or more processors and one or more non-temporary computer-readable media for storing computer-executable instructions, wherein when an instruction is executed, the system is caused to perform an operation including receiving radar data from a radar device associated with a vehicle operating in an environment, wherein the radar data indicates a detection associated with a first location in the environment; determining a radar noise level associated with a second location in the environment, at least based on the radar data; determining a vehicle safety metric associated with the vehicle; determining a radar response threshold, at least based on the vehicle safety metric; and generating a trajectory of the vehicle, at least based on comparing the radar response threshold with the radar noise level associated with the second location.

[0105]

[0109] B. The system described in paragraph A, wherein the vehicle safety metric is associated with an object type, and determining the radar response threshold is at least partially based on the radar response distribution associated with the object type.

[0106]

[0110] C. Determining the radar response threshold involves determining a first number of false positive detections associated with the radar response threshold, determining a second number of false negative detections associated with the radar response threshold, determining a third number of true positive detections associated with the radar response threshold, and the third number associated with the radar response threshold 4 The system described in paragraph A, which includes determining the number of true negative detections.

[0107]

[0111] D. The system according to paragraph A, wherein the operation is to determine a second radar noise level associated with a third location in the environment, based at least in part on the radar data, and generating the vehicle's trajectory is to generate a trajectory that excludes the second location and includes the third location, further comprising determining, at least in part, that the radar noise level associated with the second location satisfies or exceeds a radar response threshold, and that the second radar noise level associated with the third location falls below a radar response threshold.

[0108]

[0112] E. The system according to paragraph A, wherein the operation further includes determining a drivable surface metric associated with the vehicle, and determining the radar response threshold is at least partially based on the drivable surface metric.

[0109]

[0113] F. A method comprising receiving radar data associated with a region in an environment, determining radar noise data associated with the region, and evaluating the radar data at least in part on a vehicle radar response threshold and the radar noise data, wherein the radar response threshold is at least in part on a vehicle safety metric, and controlling the vehicle in the environment at least in part on the radar response threshold and the radar data.

[0110]

[0114] G. The method according to paragraph F, wherein the vehicle safety metric is associated with a first object type, and the method further comprises determining a probability associated with detecting an object of the first object type at a first location in the environment, based at least in part on the radar noise data and the radar response distribution associated with the first object type, and determining the radar response threshold, based at least in part on the probability.

[0111]

[0115] The method according to paragraph G, further comprising: H. Determining a second radar response threshold associated with a second object type based at least in part on the radar noise data and a second radar response distribution associated with the second object type; and determining a second probability associated with detecting a second object of the second object type at the first location based at least in part on the radar noise data and the second radar response distribution.

[0112]

[0116] I. The method according to paragraph F, further comprising determining a first radar response threshold, determining a first number of false-positive radar detections and a first number of false-negative radar detections associated with the first radar response threshold, determining a second radar response threshold, determining a second number of false-positive radar detections and a second number of false-negative radar detections associated with the second radar response threshold, and determining either the first radar response threshold or the second radar response threshold as the radar response threshold, at least in part on the first number of false-positive radar detections and the second number of false-positive radar detections, as well as the first number of false-negative radar detections and the second number of false-negative radar detections.

[0113]

[0117] J. The method of paragraph F, further comprising determining a drivable surface metric associated with operating the vehicle in the environment, and determining the radar response threshold based at least in part on the drivable surface metric.

[0114]

[0118] K. The method of paragraph F, further comprising determining, at least in part, a first radar noise level associated with a first location in the environment and a second radar noise level associated with a second location in the environment, based at least in part on the radar noise data, determining that the first radar noise level satisfies or exceeds the radar response threshold, and determining that the second radar noise level falls below the radar response threshold, excluding the first location and generating a trajectory of the vehicle including the second location.

[0115]

[0119] L. The method according to paragraph F, wherein determining the radar noise data includes determining a first location in the environment associated with the radar data and determining a radar noise level associated with a second location in the environment, which is at least partially based on the difference in distance from the radar device between the first location and the second location, and intensity measurements associated with the radar data.

[0116]

[0120] M. The method of paragraph L, further comprising receiving radar data from the radar device associated with the vehicle, receiving additional sensor data associated with the second location from a sensor device having different sensor means from the radar device, comparing the radar response threshold with the radar noise level associated with the second location, and determining the trajectory of the vehicle at least in part based on the additional sensor data associated with the second location.

[0117]

[0121] N. The method of paragraph F, further comprising determining a first vehicle safety metric associated with a first environment, determining a second vehicle safety metric associated with a second environment, determining the operating environment of the vehicle, and determining either the first or second vehicle safety metric as the vehicle safety metric, at least in part, based on the operating environment of the vehicle.

[0118]

[0122] O. One or more non-temporary computer-readable media storing processor-executable instructions, wherein when the instructions are executed by one or more processors, the one or more processors cause the one or more processors to perform an operation including receiving radar data associated with a region in an environment; determining radar noise data associated with the region; evaluating the radar data based at least in part on a radar response threshold for the vehicle and the radar noise data, wherein the radar response threshold is at least in part on a vehicle safety metric; and controlling the vehicle in the environment based at least in part on the radar response threshold and the radar data.

[0119]

[0123] P. The vehicle safety metric is associated with a first object type, and the operation further comprises determining a probability associated with detecting an object of the first object type at a first location in the environment, based at least in part on the radar noise data and the radar response distribution associated with the first object type, and determining the radar response threshold, based at least in part on the probability, one or more non-temporary computer-readable media as described in paragraph O.

[0120]

[0124] Q. The operation further comprises determining a second radar response threshold associated with a second object type based at least in part on the radar noise data and a second radar response distribution associated with the second object type, and determining a second probability associated with detecting a second object of the second object type at a first location based at least in part on the radar noise data and the second radar response distribution, one or more non-temporary computer-readable media as described in paragraph P.

[0121]

[0125] R. The operation further comprises determining a first radar response threshold, determining a first number of false-positive radar detections and a first number of false-negative radar detections associated with the first radar response threshold, determining a second radar response threshold, determining a second number of false-positive radar detections and a second number of false-negative radar detections associated with the second radar response threshold, and determining either the first radar response threshold or the second radar response threshold as the radar response threshold, at least in part on the first number of false-positive radar detections and the second number of false-positive radar detections, and the first number of false-negative radar detections and the second number of false-negative radar detections.

[0122]

[0126] S. The operation further comprises determining a drivable surface metric associated with operating the vehicle within the environment, and determining the radar response threshold based at least in part on the drivable surface metric, one or more non-temporary computer-readable media according to paragraph O.

[0123]

[0127] T. The operation further comprises determining, at least in part, a first radar noise level associated with a first location in the environment and a second radar noise level associated with a second location in the environment, based at least in part on the radar noise data, excluding the first location and generating a trajectory of the vehicle including the second location.

[0124]

[0128] U. A system comprising one or more processors and one or more non-temporary computer-readable media for storing computer-executable instructions, wherein when the instructions are executed, the system receives first radar data from a radar device, the first radar data indicating a detection associated with a first object in the environment, the first radar data including Doppler data and radar reflected power data associated with the first object, and receives second radar data from the radar device, the second radar data indicating a detection associated with a second possible object in the environment, the second radar data including the second possible A system that causes operations to include: including Doppler data associated with a certain object and radar reflected power data associated with a second possible object; determining a probability distribution associated with the second radar data based on the object type of the second possible object; determining an overlap between the first radar data and the second radar data; determining a probability associated with the second radar data indicating that the second possible object is an object in the environment based on the overlap and the probability distribution associated with the second radar data; and controlling a vehicle in the environment based at least in part on the probability associated with the second radar data.

[0125]

[0129] V. The system according to paragraph U, wherein controlling the vehicle includes generating a trajectory that excludes the location associated with the second radar data, at least in part on determining that the radar noise level associated with the second radar data satisfies or exceeds the radar response threshold associated with the object type.

[0126]

[0130] W. The operation comprises determining a first radar noise level and a second radar noise level associated with the second radar data, wherein the first radar noise level is a reflected power value and the second radar noise level is a Doppler value, and further comprising determining a first radar response threshold based at least in part on a reflected power distribution associated with the object type, and determining a second radar response threshold based at least in part on a Doppler distribution associated with the object type, wherein controlling the vehicle is at least in part on comparing the first radar noise level with the first radar response threshold and comparing the second radar noise level with the second radar response threshold, the system according to paragraph U.

[0127]

[0131] X. The system according to paragraph U, wherein determining the probability associated with the second radar data comprises determining a first difference in distance between the first radar data and the second radar data; determining a second difference in Doppler measurements between the first radar data and the second radar data; determining an intensity measurement associated with the first radar data; and determining a radar noise level associated with the second radar data based at least in part on the first difference, the second difference, and the intensity measurement.

[0128]

[0132] Y. Determining the probability associated with the second radar data comprises determining a distance value and an azimuth value associated with the second radar data, and determining a first reflected power threshold and a second reflected power threshold based at least in part on the distance value and the azimuth value, wherein the first reflected power threshold is associated with a first Doppler value, and the second reflected power threshold is associated with a second Doppler value, according to the system described in paragraph U.

[0129]

[0133] A method comprising: receiving radar data indicating a detection associated with a first region in an environment, wherein the radar data includes Doppler data associated with the detection; determining a radar noise level associated with a second region based at least in part on the Doppler data associated with the detection; determining a radar response threshold associated with an object type; and controlling a vehicle in the environment based at least in part on the radar noise level associated with the second region and the radar response threshold associated with the object type.

[0130]

[0134] AA. The method according to paragraph Z, wherein the radar response threshold includes at least one of the following: a Doppler value associated with the object type, a radar cross-sectional value associated with the object type, or a reflected power value associated with the object type.

[0131]

[0135] AB. The method according to paragraph Z, wherein the radar response threshold includes a first Doppler value associated with the object type and a second radar cross-sectional value associated with the object type.

[0132]

[0136] AC. The method according to paragraph Z, wherein determining the radar noise level associated with the second region includes determining a first difference between a first distance from the radar device to the first region and a second distance from the radar device to the second region, determining a second difference in Doppler measurements between the first region and the second region, and determining an intensity measurement associated with the detection.

[0133]

[0137] AD. The method according to paragraph Z, wherein determining the radar response threshold is at least partially based on the Doppler distribution associated with the object type.

[0134]

[0138] AE. The method according to paragraph Z, wherein determining the radar response threshold comprises determining a distance value and an azimuth value associated with the second region, and determining a first radar response threshold and a second radar response threshold based at least in part on the distance value and the azimuth value, the first radar response threshold being associated with a first Doppler value, and the second radar response threshold being associated with a second Doppler value.

[0135]

[0139] The method according to paragraph AE, further comprising determining a first probability associated with the first radar response threshold and a second probability associated with the second radar response threshold, at least in part on the Doppler distribution associated with the object type.

[0136]

[0140] The method according to paragraph AF, further comprising: determining a first false negative probability associated with the object type based at least in part on the first probability and the first radar response threshold; determining a second false negative probability associated with the object type based at least in part on the second probability and the second radar response threshold; and determining a third false negative probability associated with the second region based at least in part on the first false negative probability and the second false negative probability.

[0137]

[0141] AH. One or more non-temporary computer-readable media storing processor-executable instructions, wherein when the instructions are executed by one or more processors, the one or more processors cause the one or more processors to perform an operation comprising: receiving radar data indicating a detection associated with a first region in an environment, wherein the radar data includes Doppler data associated with the detection; determining a radar noise level associated with a second region based at least in part on the Doppler data associated with the detection; determining a radar response threshold associated with an object type; and controlling a vehicle in the environment based at least in part on the radar noise level associated with the second region and the radar response threshold associated with the object type.

[0138]

[0142] AI. The radar response threshold includes a first Doppler value associated with the object type and a second radar cross-sectional value associated with the object type, in one or more non-transient computer-readable media as described in paragraph AH.

[0139]

[0143] AJ. Determining the radar noise level associated with the second region comprises determining a first difference between a first distance from the radar device to the first region and a second distance from the radar device to the second region, determining a second difference in Doppler measurements between the first region and the second region, and determining an intensity measurement associated with the detection, one or more non-temporary computer-readable media as described in paragraph AH.

[0140]

[0144] AK. Determining the radar response threshold is based at least in part on the Doppler distribution associated with the object type, one or more non-transient computer-readable media as described in paragraph AH.

[0141]

[0145] AL. Determining the radar response threshold comprises determining a distance value and an azimuth value associated with the second region, and determining a first radar response threshold and a second radar response threshold based at least in part on the distance value and the azimuth value, wherein the first radar response threshold is associated with a first Doppler value, and the second radar response threshold is associated with a second Doppler value, as described in paragraph AH, one or more non-temporary computer-readable media.

[0142]

[0146] AM. The operation further comprises determining a first probability associated with the first radar response threshold and determining a second probability associated with the second radar response threshold, based at least in part on a Doppler distribution associated with the object type, one or more non-temporary computer-readable media as described in paragraph AL.

[0143]

[0147] AN. The operation further comprises determining a first false negative probability associated with the object type based at least in part on the first probability and the first radar response threshold; determining a second false negative probability associated with the object type based at least in part on the second probability and the second radar response threshold; and determining a third false negative probability associated with the second area based at least in part on the first false negative probability and the second false negative probability, as described in paragraph AM of one or more non-temporary computer-readable media.

[0144]

[0148] While the illustrative sections described above relate to specific implementations, it should be understood that, in the context of this specification, the contents of the illustrative sections can be implemented through methods, devices, systems, computer-readable media, and / or other implementations. Additionally, any of the examples from A to AN may be implemented alone or in combination with any one or more of the other examples from A to AN.

[0145] summary

[0149] While one or more examples of the techniques described herein have been explained, various modifications, additions, rearrangements, and equivalents thereof are included within the scope of the techniques described herein. For ease of understanding, the components discussed herein are described separately for illustrative purposes. However, the actions performed by various components can be combined and performed by any other component. It should also be understood that a component or step discussed in one example or implementation can be used in combination with components or steps in other examples.

[0146]

[0150] A non-exclusive list of objects in the environment may include, but is not limited to, pedestrians, animals, cyclists, trucks, motorcycles, and other vehicles. Such objects in the environment have a “geometric posture” (which may also be referred to herein simply as “posture”) that includes the overall position and / or orientation of the object relative to the reference frame. In some examples, posture may indicate the position of an object (e.g., a pedestrian), the orientation of an object, or the relative appendage positions of an object. Geometric posture may be described in two dimensions (e.g., using an xy coordinate system) or three dimensions (e.g., using an xyz or polar coordinate system) and may include the orientation of an object (e.g., roll, pitch, and / or yaw). Some objects, such as pedestrians and animals, also have what is referred to herein as “appearance posture”. Appearance posture includes the shape and / or position of body parts (e.g., appendages, head, torso, eyes, hands, feet, etc.). As used herein, the term “orientation” refers to both the “geometric orientation” of an object relative to a reference frame and the “visual orientation” in the case of pedestrians, animals, and other objects whose body parts can be modified in shape and / or position. In some examples, the reference frame is described by referring to a two- or three-dimensional coordinate system or map that describes the object’s position relative to a vehicle. However, in other examples, other reference frames may be used.

[0147]

[0151] In the illustrative descriptions, accompanying drawings, which constitute part of this specification, are referenced, and are illustrated by drawing specific examples of the claimed subject matter. It should be understood that other examples may be used, and that modifications or substitutions, such as structural changes, may be made. Such examples, modifications, or variations do not necessarily deviate from the intended scope of the claimed subject matter. The steps in this specification may be presented in a certain order, but in some cases the order may be changed so that certain inputs are provided at different times or in different orders, without changing the function and method of the described system. The disclosed procedures may also be performed in different orders. In addition, the various calculations in this specification do not need to be performed in the disclosed order, and other examples using alternative orders of calculations can be readily implemented. In addition to rearranging, calculations may also be broken down into subcalculations with the same results.

[0148]

[0152] While the subject matter is described in a language specific to structural features and / or methodological behavior, it should be understood that the subject matter as defined in the attached claims is not necessarily limited to the specific features or behaviors described. Rather, specific features and behaviors are disclosed as exemplary forms that implement the claims.

[0149]

[0153] The components described herein represent instructions that can be stored in any type of computer-readable medium and implemented in software and / or hardware. All of the methods and processes described above can be embodied in software code and / or computer-executable instructions executed by one or more computers or processors, hardware, or some combination thereof, and can be fully automated through them. Some or all of the methods may, alternatively, be embodied in specialized computer hardware.

[0150]

[0154] Unless otherwise specified, conditional terms such as “may,” “could,” “may,” or “might” are understood in context to indicate that a particular example includes a certain feature, element, and / or step not included in other examples. Therefore, such conditional terms are not generally intended to imply that a certain feature, element, and / or step is required in any way by one or more examples, or that one or more examples necessarily include logic for determining, with or without user input or prompting, whether a certain feature, element, and / or step is included in or should be performed in any specific example.

[0151]

[0155] Connecting language phrases such as "at least one of X, Y, or Z" should be understood, unless otherwise specified, to mean any item, term, etc., that includes any of X, Y, or Z, or any combination thereof. Unless explicitly stated as singular, "a" can mean singular or plural.

[0152]

[0156] The descriptions of routines, elements, or blocks in the flowcharts described herein and / or depicted in the accompanying drawings should be understood to potentially represent modules, segments, or portions of code containing one or more computer-executable instructions for implementing a particular logical function or element within the routine. Within the scope of the examples described herein, as a person skilled in the art would understand, alternative implementations may include, depending on the function in question, omitting elements or functions, or performing them in a substantially synchronous, reverse order, with additional operations, or in an order different from the one illustrated or described, such as omitting operations.

[0153]

[0157] Many variations and modifications may be made to the examples described above, and the elements thereof are understood to be included in other acceptable examples. All such modifications and variations are incorporated herein within the scope of this disclosure and are intended to be protected by the following claims.

Claims

1. A system comprising one or more processors and one or more non-temporary computer-readable media for storing computer-executable instructions, wherein when the instructions are executed, the system: Receiving radar data associated with areas within the environment, Determining radar noise data associated with the aforementioned region, Evaluating the radar data based at least in part on the vehicle's radar response threshold and the radar noise data, wherein the radar response threshold is at least in part on the vehicle safety metric. Based at least partially on the radar noise data, a first radar noise level associated with a first location in the environment and a second radar noise level associated with a second location in the environment are determined. Controlling a vehicle in the environment based at least in part on the radar response threshold and the radar data, wherein controlling the vehicle excludes the first position and includes the vehicle's trajectory including the second position. It is determined that the first radar noise level satisfies or exceeds the radar response threshold, and It is determined that the second radar noise level is below the radar response threshold. Based at least in part on, including generating, A system that performs actions including those mentioned above.

2. A system comprising one or more processors and one or more non-temporary computer-readable media for storing computer-executable instructions, wherein when an instruction is executed, the system: Receiving radar data associated with areas within the environment, Determining the radar noise data associated with the said region, wherein determining the radar noise data is Determining a first position in the environment associated with the radar data, and Determining the radar noise level associated with a second location in the environment, which includes at least in part being based on the difference in distance from the radar device between the first location and the second location, and intensity measurements associated with the radar data, Evaluating the radar data based at least in part on the vehicle's radar response threshold and the radar noise data, wherein the radar response threshold is at least in part on the vehicle safety metric. Controlling a vehicle in the environment based at least partially on the radar response threshold and the radar data, A system that performs actions including those mentioned above.

3. The vehicle safety metric is associated with a first object type, and the operation is, Based at least in part on the radar noise data and the radar response distribution associated with the first object type, the probability associated with detecting an object of the first object type at a first location in the environment is determined. Determining the radar response threshold based at least in part on the aforementioned probability, The system according to claim 1 or 2, further comprising:

4. The aforementioned operation is, A second radar response threshold associated with a second object type is determined at least in part on the radar noise data and the second radar response distribution associated with the second object type. Based at least in part on the radar noise data and the second radar response distribution, a second probability associated with detecting a second object of the second object type at the first location is determined. The system according to claim 3, further comprising:

5. The aforementioned operation is, Determining the drivable surface metrics associated with operating the vehicle within the aforementioned environment, Determining the radar response threshold based at least partially on the drivable surface metric, The system according to claim 1 or 2, further comprising:

6. Determining a first radar response threshold, Determining a first number of false-positive radar detections and a first number of false-negative radar detections associated with the first radar response threshold, To determine the second radar response threshold, Determining a second number of false-positive radar detections and a second number of false-negative radar detections associated with the second radar response threshold, Determining either the first radar response threshold or the second radar response threshold as the radar response threshold, at least in part, based on the detection of the first number of false positive radars and the second number of false positive radars, and the detection of the first number of false negative radars and the second number of false negative radars. Receiving radar data associated with areas within the environment, Determining radar noise data associated with the aforementioned region, Evaluating the radar data based at least in part on the vehicle's radar response threshold and radar noise data, wherein the radar response threshold is at least in part on a vehicle safety metric. Controlling a vehicle in the environment based at least partially on the radar response threshold and the radar data, A method that includes this.

7. Receiving radar data associated with a region in the environment, Determining radar noise data associated with the aforementioned region, Evaluating the radar data based at least in part on the vehicle's radar response threshold and the radar noise data, wherein the radar response threshold is at least in part on the vehicle safety metric. Based at least partially on the radar noise data, a first radar noise level associated with a first location in the environment and a second radar noise level associated with a second location in the environment are determined. Controlling a vehicle in the environment based at least in part on the radar response threshold and the radar data, excluding the first position and including the second position of the vehicle's trajectory, It is determined that the first radar noise level satisfies or exceeds the radar response threshold, and It is determined that the second radar noise level is below the radar response threshold. To generate, at least in part, Methods that include...

8. Receiving radar data associated with an area in the environment, Determining the radar noise data associated with the said region, wherein determining the radar noise data is Determining a first position in the environment associated with the radar data, Determining the radar noise level associated with a second location in the environment, which is at least partially based on the difference in distance from the radar device between the first location and the second location, and intensity measurements associated with the radar data, Evaluating the radar data based at least in part on the vehicle's radar response threshold and the radar noise data, wherein the radar response threshold is at least in part on the vehicle safety metric. Controlling a vehicle in the environment based at least partially on the radar response threshold and the radar data, Methods that include...

9. The vehicle safety metric is associated with a first object type, and the method is Based at least in part on the radar noise data and the radar response distribution associated with the first object type, the probability associated with detecting an object of the first object type at a first location in the environment is determined. Determining the radar response threshold based at least in part on the aforementioned probability, The method according to any one of claims 6 to 8, further comprising:

10. A second radar response threshold associated with a second object type is determined at least in part on the radar noise data and the second radar response distribution associated with the second object type. Based at least in part on the radar noise data and the second radar response distribution, a second probability associated with detecting a second object of the second object type at the first location is determined. The method according to claim 9, further comprising:

11. Determining the drivable surface metrics associated with operating the vehicle within the aforementioned environment, Determining the radar response threshold based at least partially on the drivable surface metric, The method according to any one of claims 6 to 8, further comprising:

12. To determine a first vehicle safety metric associated with a first environment, To determine a second vehicle safety metric associated with a second environment, To determine the operating environment of the aforementioned vehicle, Based at least partially on the operating environment of the vehicle, either the first vehicle safety metric or the second vehicle safety metric is determined as the vehicle safety metric. The method according to any one of claims 6 to 8, further comprising:

13. A non-temporary computer-readable medium comprising an instruction, wherein when the instruction is executed by one or more processors, the one or more processors are instructed to carry out the method according to any one of claims 6 to 8. A non-temporary computer-readable medium.

Images